# Models: top 25 of every board
# board | rank | model | score | name as published | capture date | source
# Scores come from each leaderboard's own published results, captured every day and shown exactly as each board published them; we run no evaluations. Model facts come from Hugging Face, OpenRouter and the fru.dev pricing and regions sites. The list grows as boards add new models. Logos via logo.dev; trademarks belong to their owners. Anonymous usage stats via Google Analytics.

AA Intelligence | #1 | Gemini 4 Carbon | 60.0 | as "Gemini 4 Carbon (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #2 | Claude Opus 5.5 | 59.1 | as "Claude Opus 5.5 (Max, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #3 | GPT-6 Astra | 56.9 | as "GPT-6 Astra (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #4 | GPT-6.1 Sol | 54.6 | as "GPT-6.1 Sol (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #5 | Claude Sonnet 5.5 | 54.5 | as "Claude Sonnet 5.5 (Max, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #6 | GPT-6.1 Terra | 51.3 | as "GPT-6.1 Terra (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #7 | Gemini 4 Argon | 50.4 | as "Gemini 4 Argon (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #8 | Muse Wonder Full | 50.1 | as "Muse Wonder Full (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #9 | Claude Fable 5.1 | 50.0 | as "Claude Fable 5.1 (Xhigh, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #10 | Kimi K3.1 Pro | 46.5 | as "Kimi K3.1 Pro" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #11 | Muse Wonder | 43.6 | as "Muse Wonder (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #12 | Claude Haiku 5.5 | 36.5 | as "Claude Haiku 5.5 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #13 | Grok 4.7 | 35.5 | as "Grok 4.7 (Xhigh)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #14 | Tencent Hy4 | 34.6 | as "Tencent Hy4" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #15 | Qwen3.8 Max (0902) | 33.7 | as "Qwen3.8 Max (0902)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #16 | DeepSeek V4.1 Flash | 32.6 | as "DeepSeek V4.1 Flash 1017 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #17 | GLM-5.3 | 31.7 | as "GLM-5.3 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #18 | Gemini 3.8 Flash | 30.8 | as "Gemini 3.8 Flash (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #19 | Inkling 2 Small | 30.6 | as "Inkling 2 Small" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #20 | MiMo-V2.6-Pro | 29.9 | as "MiMo-V2.6-Pro" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #21 | Ling 3.1 Flash 1019 | 29.6 | as "Ling 3.1 Flash 1019" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #22 | MiniMax-M3.1-Flash | 29.1 | as "MiniMax-M3.1-Flash" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #23 | Step 5 Preview | 28.5 | as "Step 5 Preview" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #24 | GPT-6 Luna | 27.9 | as "GPT-6 Luna (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Intelligence | #25 | GLM 5.3 Flash | 27.8 | as "GLM-5.3-Flash" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #1 | Claude Haiku 5.5 | $0.20 | as "Claude Haiku 5.5 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #2 | Inkling 2 Small | $0.47 | as "Inkling 2 Small" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #3 | DeepSeek V4.1 Flash | $0.53 | as "DeepSeek V4.1 Flash 1017 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #4 | Tencent Hy4 | $1.25 | as "Tencent Hy4" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #5 | Gemini 3.8 Flash | $1.50 | as "Gemini 3.8 Flash (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #6 | GPT-6.1 Terra | $2.00 | as "GPT-6.1 Terra (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #7 | GLM-5.3 | $2.15 | as "GLM-5.3 (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #8 | Grok 4.7 | $3.00 | as "Grok 4.7 (Xhigh)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #8 | Qwen3.8 Max (0902) | $3.00 | as "Qwen3.8 Max (0902)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #10 | Claude Sonnet 5.5 | $4.00 | as "Claude Sonnet 5.5 (Max, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #10 | GPT-6.1 Sol | $4.00 | as "GPT-6.1 Sol (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #10 | Kimi K3.1 Pro | $4.00 | as "Kimi K3.1 Pro" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #13 | Claude Opus 5.5 | $8.00 | as "Claude Opus 5.5 (Max, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #13 | Gemini 4 Argon | $8.00 | as "Gemini 4 Argon (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #13 | Gemini 4 Carbon | $8.00 | as "Gemini 4 Carbon (High)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #13 | Muse Wonder | $8.00 | as "Muse Wonder (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #17 | Claude Fable 5.1 | $20.0 | as "Claude Fable 5.1 (Xhigh, Default Fallback)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Price | #17 | GPT-6 Astra | $20.0 | as "GPT-6 Astra (Max)" | captured 2026-11-09 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #1 | MiMo-V2.6-Flash | 64 tok/s | as "MiMo-V2.6-Flash" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #2 | Qwen3.8 Max (0902) | 60 tok/s | as "Qwen3.8 Max (0902)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #3 | Qwen3.8 27B | 44 tok/s | as "Qwen3.8 27B (xhigh)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #4 | MiMo-V2.6-Pro | 43 tok/s | as "MiMo-V2.6-Pro" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #5 | GLM 5.3 Flash | 39 tok/s | as "GLM-5.3-Flash" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #6 | Kimi K3.1 Pro | 36 tok/s | as "Kimi K3.1 Pro" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #7 | Gemini 4 Carbon | 35 tok/s | as "Gemini 4 Carbon (low)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #8 | GLM-5.3 | 32 tok/s | as "GLM-5.3 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #9 | Claude Sonnet 5.5 | 31 tok/s | as "Claude Sonnet 5.5 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #10 | Gemini 4 Argon | 28 tok/s | as "Gemini 4 Argon (high)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #11 | Claude Opus 5.5 | 25 tok/s | as "Claude Opus 5.5 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #12 | Grok 4.7 | 24 tok/s | as "Grok 4.7 (xhigh)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #13 | DeepSeek V4 Pro 0813 | 23 tok/s | as "DeepSeek V4 Pro 0813 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #14 | Claude Fable 5.1 | 22 tok/s | as "Claude Fable 5.1 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #15 | GPT-6.1 Sol | 22 tok/s | as "GPT-6.1 Sol (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #16 | GPT-6 Astra | 21 tok/s | as "GPT-6 Astra (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #17 | MiniMax-M3.1-Flash | 17 tok/s | as "MiniMax-M3.1-Flash" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #18 | Inkling 2 Small | 17 tok/s | as "Inkling 2 Small" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #19 | Claude Haiku 5.5 | 16 tok/s | as "Claude Haiku 5.5 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #20 | Gemini 3.8 Flash | 15 tok/s | as "Gemini 3.8 Flash (high)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #21 | Mistral Large 4 High | 14 tok/s | as "Mistral Large 4 (high)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #22 | Step 5 Preview | 14 tok/s | as "Step 5 Preview" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #23 | Tencent Hy4 | 14 tok/s | as "Tencent Hy4" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #24 | GPT-6.1 Terra | 14 tok/s | as "GPT-6.1 Terra (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
AA Speed | #25 | DeepSeek V4.1 Flash | 14 tok/s | as "DeepSeek V4.1 Flash 1017 (max)" | captured 2026-11-07 | https://artificialanalysis.ai/leaderboards/models
Speech Arena | #1 | Eleven V4 | 1,339 | as "Eleven v4" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #2 | Eleven V4 Turbo | 1,335 | as "Eleven v4 Turbo" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #3 | Qwen Audio 3.1 TTS Plus | 1,303 | as "Qwen-Audio-3.1-TTS-Plus" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #4 | Sonic 3.6 | 1,297 | as "Sonic 3.6" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #5 | Simba 3.5 | 1,286 | as "Simba 3.5" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #6 | Gemini 3.8 Flash TTS | 1,283 | as "Gemini 3.8 Flash TTS" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #7 | Fish Audio Drama 3 | 1,275 | as "Fish Audio Drama 3" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #8 | Lightning V3.1 Pro | 1,273 | as "Lightning V3.1 Pro (Oct 2026)" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #9 | Qwen Audio 3.0 TTS Plus | 1,268 | as "Qwen-Audio-3.0-TTS-Plus" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #10 | Realtime TTS 2 | 1,268 | as "Realtime TTS-2" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #11 | Gemini 3.8 Flash Lite TTS | 1,260 | as "Gemini 3.8 Flash-Lite TTS" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #12 | Simba 3.2 | 1,250 | as "Simba 3.2" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #13 | Breeze TTS 2 | 1,228 | as "Breeze TTS 2" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #14 | Assemblyai TTS 1 | 1,224 | as "AssemblyAI-TTS-1" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #15 | Voxtral 3 TTS | 1,217 | as "Voxtral 3 TTS" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #16 | Realtime TTS 2 Flash | 1,217 | as "Realtime TTS-2 Flash" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #17 | V3 Conversational | 1,216 | as "v3 Conversational" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #18 | Stepaudio 2.5 TTS | 1,216 | as "StepAudio 2.5 TTS (Aug 2026)" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #19 | Gemini 3.1 Flash TTS | 1,215 | as "Gemini 3.1 Flash TTS" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #20 | Luna TTS | 1,204 | as "Luna TTS" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #21 | Sonic 3.5 | 1,196 | as "Sonic 3.5" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #22 | Eleven V3 | 1,189 | as "Eleven v3" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #23 | Fish Audio S2.1 Pro | 1,188 | as "Fish Audio S2.1 Pro (Oct 2026)" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #24 | Ming 3.0 TTS | 1,187 | as "Ming-3.0-tts" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Speech Arena | #25 | Soniox TTS Real Time V2 | 1,181 | as "Soniox TTS Real-Time v2" | captured 2026-11-09 | https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
Aider Polyglot | #1 | GPT-5 | 88.0% | as "gpt-5 (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #2 | o3-pro | 84.9% | as "o3-pro (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #3 | Gemini 2.5 Pro (Jun 2025) | 83.1% | as "gemini-2.5-pro-preview-06-05 (32k think)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #4 | o3 | 81.3% | as "o3 (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #5 | Grok 4 | 79.6% | as "grok-4 (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #6 | o3 GPT 4.1 | 78.2% | as "o3 (high) + gpt-4.1" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #7 | Gemini 2.5 Pro 05 06 | 76.9% | as "Gemini 2.5 Pro Preview 05-06" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #8 | DeepSeek-V3.2 | 74.2% | as "DeepSeek-V3.2-Exp (Reasoner)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #9 | Gemini 2.5 Pro 03 25 | 72.9% | as "Gemini 2.5 Pro Preview 03-25" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #10 | Claude Opus 4 | 72.0% | as "claude-opus-4-20250514 (32k thinking)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #10 | o4-mini | 72.0% | as "o4-mini (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #12 | DeepSeek-R1 (May 2025) | 71.4% | as "DeepSeek R1 (0528)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #13 | Claude 3.7 Sonnet | 64.9% | as "claude-3-7-sonnet-20250219 (32k thinking tokens)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #14 | DeepSeek R1 Claude 3 5 Sonnet | 64.0% | as "DeepSeek R1 + claude-3-5-sonnet-20241022" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #15 | o1 | 61.7% | as "o1-2024-12-17 (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #16 | Claude Sonnet 4 | 61.3% | as "claude-sonnet-4-20250514 (32k thinking)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #17 | o3 Mini | 60.4% | as "o3-mini (high)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #18 | Qwen3 235b A22B Diff No Alibaba | 59.6% | as "Qwen3 235B A22B diff, no think, Alibaba API" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #19 | Kimi K2 Thinking | 59.1% | as "Kimi K2" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #20 | DeepSeek V3 | 55.1% | as "DeepSeek V3 (0324)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #20 | Gemini 2.5 Flash (Sep 2025) | 55.1% | as "gemini-2.5-flash-preview-05-20 (24k think)" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #22 | Quasar Alpha | 54.7% | as "Quasar Alpha" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #23 | Grok 3 | 53.3% | as "Grok 3 Beta" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #24 | Optimus Alpha | 52.9% | as "Optimus Alpha" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
Aider Polyglot | #25 | GPT 4.1 | 52.4% | as "gpt-4.1" | captured 2026-11-09 | https://aider.chat/docs/leaderboards/
ARC-AGI-2 | #1 | GPT-6 Astra | 95.0% | as "GPT-6 Astra (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #2 | GPT-6.1 Sol | 94.2% | as "GPT-6.1 Sol (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #3 | Claude Opus 5.5 | 93.3% | as "Claude Opus 5.5 (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #4 | GPT-5.6 Sol | 92.5% | as "GPT-5.6 Sol (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #5 | Gemini 4 Argon | 91.3% | as "Gemini 4 Argon (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #6 | Claude Opus 5 | 90.4% | as "Claude Opus 5 (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #7 | Claude Fable 5.1 | 90.0% | as "Claude Fable 5.1 (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #8 | GPT-6 Sol | 89.6% | as "GPT-6 Sol (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #9 | Claude Fable 5 | 89.2% | as "Claude Fable 5 (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #9 | Gemini 3.8 Flash | 89.2% | as "Gemini 3.8 Flash (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #11 | GPT-5.5 | 85.0% | as "GPT-5.5 (XHigh)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #12 | Gemini 3.7 Flash | 84.6% | as "Gemini 3.7 Flash (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #13 | Gemini 3 | 84.6% | as "Gemini 3 Deep Think (2/26)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #13 | GPT-5.5 Pro | 84.6% | as "GPT-5.5 Pro (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #15 | GPT-5.6 Terra | 83.9% | as "GPT-5.6 Terra (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #16 | Claude Sonnet 5.5 | 83.9% | as "Claude Sonnet 5.5 (XHigh)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #17 | GPT-5.4 Pro | 83.3% | as "GPT-5.4 Pro (XHigh)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #18 | Inkling 2 Small | 81.7% | as "Inkling 2 Small (XHigh)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #19 | DeepSeek V4.1 Flash | 78.1% | as "DeepSeek V4.1 Flash 1017 (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #20 | Gemini 3.1 Pro Preview | 77.1% | as "Gemini 3.1 Pro (Preview)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #21 | Dots3 Note | 76.8% | as "Dots3-Note Preview (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #22 | Claude 4.7 | 75.8% | as "Claude 4.7 (Max)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #23 | GPT-5.4 | 74.0% | as "GPT-5.4 (XHigh)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #24 | Claude Opus 4.8 | 72.1% | as "Claude Opus 4.8 (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
ARC-AGI-2 | #24 | Gemini 3.5 Flash | 72.1% | as "Gemini 3.5 Flash (High)" | captured 2026-11-09 | https://arcprize.org/leaderboard
BFCL | #1 | Claude Opus 4.5 | 77.5% | as "Claude-Opus-4-5-20251101 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #2 | Claude Sonnet 4.5 | 73.2% | as "Claude-Sonnet-4-5-20250929 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #3 | Gemini 3 Pro | 72.5% | as "Gemini-3-Pro-Preview (Prompt)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #4 | GLM 4.6 | 72.4% | as "GLM-4.6 (FC thinking)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #5 | Grok 4 1 Fast | 69.6% | as "Grok-4-1-fast-reasoning (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #6 | Claude 4.5 Haiku | 68.7% | as "Claude-Haiku-4-5-20251001 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #7 | o3 | 63.0% | as "o3-2025-04-16 (Prompt)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #8 | Grok 4 | 63.0% | as "Grok-4-0709 (Prompt)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #9 | Moonshotai Kimi K2 | 59.1% | as "Moonshotai-Kimi-K2-Instruct (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #10 | Grok 4 1 Fast Non | 58.3% | as "Grok-4-1-fast-non-reasoning (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #11 | Command A+ | 57.1% | as "Command A Reasoning (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #12 | DeepSeek-V3.2 | 56.7% | as "DeepSeek-V3.2-Exp (Prompt + Thinking)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #13 | Gemini 2.5 Flash (Sep 2025) | 56.2% | as "Gemini-2.5-Flash (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #14 | GPT-5.2 | 55.9% | as "GPT-5.2-2025-12-11 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #15 | GPT-5 mini | 55.5% | as "GPT-5-mini-2025-08-07 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #16 | Xlam 2 32b Fc R | 54.7% | as "xLAM-2-32b-fc-r (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #17 | GPT 4.1 | 54.0% | as "GPT-4.1-2025-04-14 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #18 | o4-mini | 53.2% | as "o4-mini-2025-04-16 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #19 | Xlam 2 70b Fc R | 53.1% | as "xLAM-2-70b-fc-r (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #20 | Qwen3-235B-A22B-Thinking (Jul 2025) | 52.1% | as "Qwen3-235B-A22B-Instruct-2507 (Prompt)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #21 | GPT 5 nano | 51.5% | as "GPT-5-nano-2025-08-07 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #22 | Nanbeige4 3b | 51.4% | as "Nanbeige4-3B-Thinking-2511 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #23 | GPT 4.1 mini | 50.5% | as "GPT-4.1-mini-2025-04-14 (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #24 | Qwen3 32b | 48.7% | as "Qwen3-32B (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL | #25 | Nanbeige3.5 Pro | 47.7% | as "Nanbeige3.5-Pro-Thinking (FC)" | captured 2026-11-09 | https://gorilla.cs.berkeley.edu/leaderboard.html
Epoch ECI | #1 | GPT-6 Astra | 169.1 | as "GPT-6 Astra" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #2 | GPT-6.1 Sol | 168.9 | as "GPT-6.1 Sol" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #3 | Claude Opus 5.5 | 168.4 | as "Claude Opus 5.5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #4 | GPT-6.1 Terra | 167.8 | as "GPT-6.1 Terra" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #5 | Claude Fable 5.1 | 166.9 | as "Claude Fable 5.1" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #6 | Gemini 4 Argon | 166.4 | as "Gemini 4 Argon" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #7 | Claude Sonnet 5.5 | 166.2 | as "Claude Sonnet 5.5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #8 | Claude Opus 5 | 164.4 | as "Claude Opus 5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #9 | Claude Fable 5 | 164.2 | as "Claude Fable 5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #10 | GPT-6 Sol | 164.1 | as "GPT-6 Sol" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #11 | GPT-5.6 Sol | 163.0 | as "GPT-5.6 Sol" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #12 | GPT-5.5 Pro | 162.7 | as "GPT-5.5 Pro" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #13 | Muse Wonder | 162.0 | as "Muse Wonder" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #14 | GPT-5.6 Terra | 160.9 | as "GPT-5.6 Terra" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #15 | Claude Haiku 5.5 | 160.2 | as "Claude Haiku 5.5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #16 | GPT-5.4 Pro | 160.2 | as "GPT-5.4 Pro" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #17 | GPT-5.5 | 160.0 | as "GPT-5.5" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #18 | Claude Opus 4.8 | 159.9 | as "Claude Opus 4.8" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #19 | DeepSeek V4.1 Flash | 159.3 | as "DeepSeek V4.1 Flash 1017" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #20 | Gemini 3.8 Flash | 158.6 | as "Gemini 3.8 Flash" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #21 | Kimi K3 | 158.5 | as "Kimi K3" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #22 | Gemini 3.7 Flash | 158.4 | as "Gemini 3.7 Flash" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #23 | Muse Spark 1.3 | 158.0 | as "Muse Spark 1.3" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #24 | Grok 4.6 | 157.9 | as "Grok 4.6" | captured 2026-11-09 | https://epoch.ai/eci
Epoch ECI | #25 | GPT-5.4 | 157.8 | as "GPT-5.4" | captured 2026-11-09 | https://epoch.ai/eci
GPQA Diamond | #1 | Gemini 4 Argon | 96.4% | as "gemini-4-argon_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #2 | GPT-6 Astra | 95.8% | as "gpt-6-astra_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #3 | Claude Sonnet 5.5 | 95.6% | as "claude-sonnet-5-5_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #4 | Gemini 3.8 Flash | 95.4% | as "gemini-3.8-flash_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #4 | GPT-6.1 Sol | 95.4% | as "gpt-6.1-sol_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #6 | Gemini 3.7 Flash | 94.8% | as "gemini-3.7-flash_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #7 | GPT-5.4 Pro | 94.6% | as "gpt-5.4-pro-2026-03-05_xhigh" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #8 | Gemini 3.1 Pro Preview | 94.4% | as "gemini-3.1-pro-preview_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #9 | GPT-6.1 Terra | 94.3% | as "gpt-6.1-terra_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #9 | GPT-6 Sol | 94.3% | as "gpt-6-sol_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #11 | Kimi K3.1 Pro Together | 94.2% | as "kimi-k3.1-pro-together_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #12 | Gemini 3.6 Flash | 94.1% | as "gemini-3.6-flash_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #13 | GPT-5.5 Pre Release | 94.0% | as "gpt-5.5-pre-release_xhigh" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #13 | Grok 4.6 | 94.0% | as "grok-4.6_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #15 | GPT-5.5 Pro Pre Release | 93.9% | as "gpt-5.5-pro-pre-release_xhigh" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #16 | Claude Opus 5 | 93.9% | as "claude-opus-5_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #17 | GPT-5.6 Sol | 93.5% | as "gpt-5.6-sol_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #18 | Grok 4.5 | 93.4% | as "grok-4.5_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #19 | GPT-5.6 Terra | 93.3% | as "gpt-5.6-terra_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #20 | GPT-5.4 | 93.3% | as "gpt-5.4-2026-03-05_xhigh" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #21 | DeepSeek V4.1 Flash | 93.2% | as "deepseek-v4.1-flash-1017_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #22 | Doubao Seed Evolving | 93.1% | as "doubao-seed-evolving_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #22 | Kimi K3 | 93.1% | as "kimi-k3_max" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #24 | Gemini 3.5 Flash | 92.8% | as "gemini-3.5-flash_high" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
GPQA Diamond | #25 | Grok 4.7 | 92.7% | as "grok-4.7_xhigh" | captured 2026-11-09 | https://epoch.ai/benchmarks/gpqa-diamond
LiveBench | #1 | Claude Fable 5.1 | 83.4% | as "claude-fable-5-1-max-effort" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #2 | Claude Opus 5.5 | 83.2% | as "claude-opus-5-5-max-effort" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #3 | Claude Fable 5 | 83.0% | as "claude-fable-5-max-effort" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #4 | GPT-6 Astra | 82.2% | as "gpt-6-astra-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #5 | GPT-6.1 Sol | 81.6% | as "gpt-6.1-sol-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #6 | Muse Spark 1.3 | 81.6% | as "muse-spark-1.3-xhigh" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #7 | Muse Wonder 1.0 Max Effort | 81.2% | as "muse-wonder-1.0-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #8 | DeepSeek V4.1 Flash | 81.1% | as "deepseek-v4.1-flash-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #9 | GPT-5.6 Sol | 81.0% | as "gpt-5.6-sol-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #10 | GPT-5.5 | 80.2% | as "gpt-5.5-xhigh" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #11 | Claude Opus 5 | 80.1% | as "claude-opus-5-max-effort" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #12 | Smaug Agentic | 79.5% | as "smaug-agentic" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #13 | GPT-6 Sol | 79.3% | as "gpt-6-sol-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #14 | Kimi K3 | 79.2% | as "kimi-k3" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #15 | Gemini 3.7 Flash | 78.8% | as "gemini-3.7-flash-high" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #16 | Qwen3.8 Max (0902) | 78.5% | as "qwen3.8-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #17 | Grok 4.6 | 78.0% | as "grok-4.6" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #18 | GPT-5.4 | 78.0% | as "gpt-5.4-xhigh" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #19 | Muse Spark 1.2 | 78.0% | as "muse-spark-1.2-xhigh" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #20 | GPT-5.6 Terra | 77.9% | as "gpt-5.6-terra-max" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #21 | Claude Sonnet 5.5 | 77.8% | as "claude-sonnet-5-5-xhigh-effort" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #22 | DeepSeek V4 Pro 0813 | 77.4% | as "deepseek-v4-pro-0813" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #22 | Smaug Flash | 77.4% | as "smaug-flash" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #24 | Grok 4.7 | 77.4% | as "grok-4.7-xhigh" | captured 2026-11-09 | https://livebench.ai/
LiveBench | #25 | Gemini 3.1 Pro Preview | 77.0% | as "gemini-3.1-pro-preview-high" | captured 2026-11-09 | https://livebench.ai/
Document Arena | #1 | Claude Fable 5 | 1,499 | as "Claude Fable 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #2 | Claude Fable 5.1 | 1,499 | as "Claude Fable 5.1 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #3 | Claude Opus 4.6 | 1,496 | as "Claude Opus 4.6 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #4 | Claude Opus 4.7 | 1,495 | as "Claude Opus 4.7" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #5 | GPT-5.6 Sol | 1,486 | as "GPT-5.6 Sol (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #6 | Claude Opus 5 | 1,486 | as "Claude Opus 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #7 | Claude Opus 4.8 | 1,486 | as "Claude Opus 4.8 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #8 | GPT-5.5 | 1,482 | as "GPT-5.5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #9 | Muse Spark 1.1 | 1,479 | as "Muse Spark 1.1" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #10 | Claude Sonnet 4.6 | 1,478 | as "Claude Sonnet 4.6" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #11 | GPT-6 Astra | 1,477 | as "GPT-6 Astra (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #12 | Muse Spark 1.3 | 1,474 | as "Muse Spark 1.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #13 | GPT-5.6 Terra | 1,474 | as "GPT-5.6 Terra (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #14 | GPT-5.4 | 1,471 | as "GPT-5.4" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #15 | Claude Sonnet 5 | 1,469 | as "Claude Sonnet 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #16 | Gemini 3.8 Flash | 1,469 | as "Gemini 3.8 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #17 | Gemini 3.7 Flash | 1,468 | as "Gemini 3.7 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #18 | Claude Opus 4.5 | 1,468 | as "Claude Opus 4.5 (20251101)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #19 | Muse Spark | 1,466 | as "Muse Spark" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #20 | Grok 4.5 | 1,466 | as "Grok 4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #21 | GPT-5.6 Luna | 1,460 | as "GPT-5.6 Luna (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #22 | GPT-5.5 Instant (June 2026) | 1,459 | as "GPT-5.5 Instant" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #23 | Gemini 3.1 Pro Preview | 1,459 | as "Gemini 3.1 Pro Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #24 | Gemini 3.5 Flash | 1,458 | as "Gemini 3.5 Flash (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Document Arena | #25 | Gemini 3.6 Flash | 1,454 | as "Gemini 3.6 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/document
Image Edit | #1 | GPT Image 2.5 Sunburst | 1,517 | as "GPT-Image-2.5 Sunburst" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #2 | GPT Image 2.5 Flare | 1,483 | as "GPT-Image-2.5 Flare" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #3 | GPT Image 2.6 Sunburst | 1,476 | as "GPT-Image-2.6 Sunburst (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #4 | MAI Image 2.7 | 1,467 | as "MAI-Image-2.7-Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #5 | GPT Image 2.6 Flare | 1,462 | as "GPT-Image-2.6 Flare (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #6 | GPT Image 2 | 1,460 | as "GPT-Image-2 (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #7 | Grok Imagine Image 2.0 | 1,438 | as "Grok Imagine Image 2.0" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #8 | Gemini Nano Banana 2.1 | 1,427 | as "Gemini Nano Banana 2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #9 | MAI Image 2.6 | 1,427 | as "MAI-Image-2.6" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #10 | Krea 3 Ultra | 1,411 | as "Krea 3 Ultra" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #11 | MAI Image 2.5 | 1,400 | as "MAI-Image-2.5" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #12 | Muse Image | 1,399 | as "Muse Image" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #13 | Seedream 5.0 Pro | 1,391 | as "Seedream 5.0 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #14 | Grok Imagine Image | 1,391 | as "Grok Imagine Image (Quality, 20260519)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #15 | Gemini 3 Pro Image | 1,390 | as "Gemini 3 Pro Image (nano-banana-pro, 2K)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #16 | Gemini 3.1 Flash Image | 1,387 | as "Gemini 3.1 Flash Image (nano-banana-2, Web Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #17 | GPT Image | 1,386 | as "ChatGPT Image Latest (High Fidelity, 20251216)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #18 | Reve 2.1 | 1,374 | as "Reve 2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #19 | GPT Image 1.5 | 1,368 | as "GPT-Image-1.5 (High Fidelity)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #20 | Qwen Image 2.1 | 1,364 | as "Qwen-Image-2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #21 | Reve 2.0 | 1,358 | as "Reve 2.0" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #22 | Ideogram 4.5 | 1,345 | as "Ideogram 4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #23 | Uni 1.1 | 1,334 | as "UNI-1.1 Max" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #24 | Gemini 3.1 Flash Lite Image | 1,313 | as "Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image Edit | #25 | Seedream 4.5 | 1,303 | as "Seedream 4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/image-edit
Image-to-Video | #1 | Gemini Omni 1.2 Flash | 1,502 | as "Gemini Omni 1.2 Flash" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #2 | MiniMax H3 | 1,493 | as "MiniMax H3" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #3 | Dreamina Seedance 2.5 | 1,488 | as "Dreamina Seedance 2.5 (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #4 | Gemini Omni 1.1 Flash | 1,486 | as "Gemini Omni 1.1 Flash" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #5 | Wan 3.0 | 1,481 | as "Wan 3.0" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #6 | Dreamina Seedance 2.0 | 1,479 | as "Dreamina Seedance 2.0 (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #7 | Skyreels V4 | 1,476 | as "SkyReels V4" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #8 | Gemini Omni Flash | 1,463 | as "gemini-omni-flash" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #9 | Hidream o1 Video 1.0 | 1,455 | as "HiDream-O1-Video-1.0" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #10 | Grok Imagine Video 1.5 | 1,454 | as "Grok Imagine Video 1.5 (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #11 | Flux 3 Video | 1,451 | as "FLUX 3 Video (20260811)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #12 | Happyhorse 1.0 | 1,443 | as "HappyHorse 1.0" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #13 | Wan 2.7 | 1,428 | as "Wan 2.7" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #14 | Grok Imagine Video | 1,412 | as "Grok Imagine Video (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #15 | Veo 3.1 | 1,399 | as "Veo 3.1 (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #16 | Veo 3.1 Fast | 1,386 | as "Veo 3.1 Fast (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #17 | Vidu Q3 Pro | 1,363 | as "Vidu Q3 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #18 | Kling 3.0 Pro | 1,353 | as "Kling 3.0 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #19 | Veo 3 | 1,332 | as "Veo 3 (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #20 | Veo 3 Fast | 1,327 | as "Veo 3 Fast (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #21 | Wan 2.5 | 1,322 | as "Wan 2.5 Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #22 | Wan 2.6 | 1,309 | as "Wan 2.6" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #23 | Seedance 1.5 Pro | 1,307 | as "Seedance 1.5 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #24 | Pixverse V5.6 | 1,299 | as "PixVerse V5.6" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Image-to-Video | #25 | Kling 2.6 Pro | 1,294 | as "Kling 2.6 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/image-to-video
Search Arena | #1 | GPT-5.6 Sol | 1,255 | as "GPT-5.6 Sol (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #2 | GPT-6.1 Sol | 1,247 | as "GPT-6.1 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #3 | GPT-6 Astra | 1,245 | as "GPT-6 Astra (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #4 | GPT-6 Sol | 1,230 | as "GPT-6 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #5 | Claude Fable 5 | 1,229 | as "Claude Fable 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #6 | Qwen3.8 Max (0902) | 1,228 | as "Qwen3.8-Max" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #7 | Claude Fable 5.1 | 1,227 | as "Claude Fable 5.1 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #8 | GPT-5.5 | 1,227 | as "GPT-5.5 (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #9 | Claude Opus 4.6 | 1,222 | as "Claude Opus 4.6 (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #10 | Claude Opus 5 | 1,213 | as "Claude Opus 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #11 | Claude Opus 5.5 | 1,213 | as "Claude Opus 5.5 (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #12 | Claude Opus 4.7 | 1,210 | as "Claude Opus 4.7" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #13 | GPT-6 Luna | 1,210 | as "GPT-6 Luna (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #14 | Gemini 3.1 Pro Preview | 1,208 | as "Gemini 3.1 Pro (Grounding)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #15 | Grok 4.20 Multi Agent | 1,206 | as "Grok 4.20 Multi-Agent Beta (0309)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #16 | Grok 4.5 | 1,205 | as "Grok 4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #17 | Claude Sonnet 4.6 | 1,201 | as "Claude Sonnet 4.6 (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #18 | Gemini 3 Pro | 1,200 | as "Gemini 3 Pro (Grounding)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #19 | Grok 4.20 1 | 1,199 | as "Grok 4.20 Beta 1" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #20 | o3 | 1,197 | as "o3 (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #21 | GPT-5.4 | 1,196 | as "GPT-5.4 (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #22 | Grok 4 1 Fast | 1,195 | as "Grok 4.1 Fast (Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #23 | Claude Opus 4.8 | 1,195 | as "Claude Opus 4.8" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #24 | Grok 4.3 Beta | 1,193 | as "Grok 4.3" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Search Arena | #25 | Ernie 5.1 | 1,192 | as "ERNIE 5.1" | captured 2026-11-08 | https://arena.ai/leaderboard/search
Text Arena | #1 | Gemini 4 Carbon | 1,526 | as "Gemini 4 Carbon (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #2 | Gemini 4 Argon | 1,523 | as "Gemini 4 Argon (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #3 | Muse Wonder | 1,513 | as "Muse Wonder (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #4 | Claude Opus 5.5 | 1,505 | as "Claude Opus 5.5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #5 | Claude Fable 5 | 1,504 | as "Claude Fable 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #6 | Claude Fable 5.1 | 1,504 | as "Claude Fable 5.1 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #7 | Claude Opus 4.6 | 1,503 | as "Claude Opus 4.6 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #8 | Claude Opus 4.7 | 1,501 | as "Claude Opus 4.7 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #9 | Gemini 3.8 Flash | 1,498 | as "Gemini 3.8 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #10 | Muse Spark 1.3 | 1,495 | as "Muse Spark 1.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #11 | Muse Spark 1.2 | 1,493 | as "Muse Spark 1.2 (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #12 | Claude Opus 5 | 1,490 | as "Claude Opus 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #13 | Muse Spark 1.1 | 1,490 | as "Muse Spark 1.1" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #14 | Muse Spark | 1,489 | as "Muse Spark" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #15 | Gemini 3.7 Flash | 1,489 | as "Gemini 3.7 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #16 | Kimi K3 | 1,488 | as "Kimi K3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #17 | Gemini 3.1 Pro Preview | 1,487 | as "Gemini 3.1 Pro Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #18 | Gemini 3 Pro | 1,486 | as "Gemini 3 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #19 | GPT-5.6 Sol | 1,485 | as "GPT-5.6 Sol (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #20 | Qwen3.8 Max (0902) | 1,483 | as "Qwen3.8-Max" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #21 | GPT-6.1 Sol | 1,483 | as "GPT-6.1 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #22 | Gemini 3.6 Flash | 1,483 | as "Gemini 3.6 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #23 | GLM-5.3 | 1,482 | as "GLM-5.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #24 | Claude Opus 4.8 | 1,482 | as "Claude Opus 4.8 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text Arena | #25 | GPT-5.5 | 1,481 | as "GPT-5.5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/text
Text-to-Image | #1 | GPT Image 2.5 Sunburst | 1,429 | as "GPT-Image-2.5 Sunburst" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #2 | GPT Image 2.6 Sunburst | 1,409 | as "GPT-Image-2.6 Sunburst (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #3 | GPT Image 2.5 Flare | 1,402 | as "GPT-Image-2.5 Flare" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #4 | GPT Image 2.6 Flare | 1,383 | as "GPT-Image-2.6 Flare (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #5 | GPT Image 2 | 1,382 | as "GPT-Image-2 (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #6 | MAI Image 2.6 | 1,330 | as "MAI-Image-2.6" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #7 | Gemini Nano Banana 2.1 | 1,325 | as "Gemini Nano Banana 2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #8 | Grok Imagine Image 2.0 | 1,318 | as "Grok Imagine Image 2.0" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #9 | Reve 2.1 | 1,300 | as "Reve 2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #10 | Muse Image | 1,268 | as "Muse Image" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #11 | Reve 2.0 | 1,268 | as "Reve 2.0" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #12 | Gemini 3.1 Flash Image | 1,257 | as "Gemini 3.1 Flash Image (nano-banana-2, Web Search)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #13 | Qwen Image 3.0 Pro | 1,254 | as "Qwen-Image-3.0-Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #14 | MAI Image 2.5 | 1,253 | as "MAI-Image-2.5" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #15 | Seedream 5.0 Pro | 1,250 | as "Seedream 5.0 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #16 | Gemini 3.1 Flash Lite Image | 1,249 | as "Gemini 3.1 Flash-Lite Image (nano-banana-2-lite)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #17 | Gemini 3 Pro Image | 1,246 | as "Gemini 3 Pro Image (nano-banana-pro, 2K)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #18 | GPT Image 1.5 | 1,236 | as "GPT-Image-1.5 (High Fidelity)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #19 | Qwen Image 2.1 | 1,227 | as "Qwen-Image-2.1" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #20 | Ideogram 4.0 | 1,199 | as "Ideogram 4.0 (Quality)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #21 | Qwen Image 2.0 Pro | 1,192 | as "Qwen-Image-2.0-Pro (2026-06-22)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #22 | Uni 1.1 | 1,189 | as "UNI-1.1 Max" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #23 | MAI Image 2 | 1,183 | as "MAI-Image-2" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #24 | Grok Imagine Image | 1,169 | as "Grok Imagine Image" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Image | #25 | Recraft V4.1 Utility Pro | 1,169 | as "Recraft V4.1 Utility Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-image
Text-to-Video | #1 | Gemini Omni 1.2 Flash | 1,541 | as "Gemini Omni 1.2 Flash" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #2 | Gemini Omni 1.1 Flash | 1,514 | as "Gemini Omni 1.1 Flash" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #3 | Gemini Omni Flash | 1,509 | as "gemini-omni-flash" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #4 | Flux 3 Video | 1,491 | as "FLUX 3 Video" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #5 | Grok Imagine Video 1.5 | 1,486 | as "Grok Imagine Video 1.5" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #6 | Dreamina Seedance 2.0 | 1,481 | as "Dreamina Seedance 2.0 (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #7 | Dreamina Seedance 2.5 | 1,480 | as "Dreamina Seedance 2.5 (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #8 | Wan 3.0 | 1,477 | as "Wan 3.0" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #9 | Skyreels V4 | 1,458 | as "SkyReels V4" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #10 | Muse Video | 1,457 | as "Muse Video" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #11 | MiniMax H3 | 1,457 | as "MiniMax H3" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #12 | Happyhorse 1.0 | 1,428 | as "HappyHorse 1.0" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #13 | Sora 2 Pro | 1,367 | as "Sora 2 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #14 | Veo 3.1 | 1,363 | as "Veo 3.1 (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #15 | Veo 3.1 Fast | 1,361 | as "Veo 3.1 Fast (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #16 | Veo 3 Fast | 1,347 | as "Veo 3 Fast (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #17 | Sora 2 | 1,343 | as "Sora 2" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #18 | Grok Imagine Video | 1,341 | as "Grok Imagine Video (720p)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #19 | Veo 3 | 1,341 | as "Veo 3 (Audio)" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #20 | Wan 2.7 | 1,337 | as "Wan 2.7" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #21 | Wan 2.6 | 1,324 | as "Wan 2.6" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #22 | Seedance 1.5 Pro | 1,256 | as "Seedance 1.5 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #23 | Wan 2.5 | 1,244 | as "Wan 2.5 Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #24 | Pixverse V5.6 | 1,238 | as "PixVerse V5.6" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Text-to-Video | #25 | Runway Gen 4.5 | 1,223 | as "Runway Gen-4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/text-to-video
Vision Arena | #1 | Claude Fable 5 | 1,309 | as "Claude Fable 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #2 | Qwen3.8 Max (0902) | 1,300 | as "Qwen3.8-Max" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #3 | Claude Opus 4.7 | 1,299 | as "Claude Opus 4.7" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #4 | Claude Opus 4.6 | 1,299 | as "Claude Opus 4.6 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #5 | Claude Opus 5.5 | 1,296 | as "Claude Opus 5.5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #6 | Gemini 3.7 Flash | 1,294 | as "Gemini 3.7 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #7 | Muse Spark | 1,294 | as "Muse Spark" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #8 | GPT-6.1 Sol | 1,293 | as "GPT-6.1 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #9 | Gemini 3.8 Flash | 1,293 | as "Gemini 3.8 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #10 | Muse Spark 1.2 | 1,292 | as "Muse Spark 1.2 (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #11 | Muse Spark 1.3 | 1,290 | as "Muse Spark 1.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #12 | Gemini 3 Pro | 1,289 | as "Gemini 3 Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #13 | Claude Fable 5.1 | 1,288 | as "Claude Fable 5.1 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #14 | GPT-5.6 Sol | 1,288 | as "GPT-5.6 Sol (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #15 | Claude Opus 4.8 | 1,286 | as "Claude Opus 4.8 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #16 | Claude Opus 5 | 1,285 | as "Claude Opus 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #17 | GPT-6 Astra | 1,285 | as "GPT-6 Astra (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #18 | GPT-5.5 | 1,285 | as "GPT-5.5" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #19 | GPT-5.4 | 1,282 | as "GPT-5.4 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #20 | Gemini 3.5 Flash | 1,282 | as "Gemini 3.5 Flash (Medium)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #21 | Grok 4.5 | 1,281 | as "Grok 4.5" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #22 | Gemini 3.1 Pro Preview | 1,280 | as "Gemini 3.1 Pro Preview" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #23 | Gemini 3.6 Flash | 1,280 | as "Gemini 3.6 Flash (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #24 | Muse Spark 1.1 | 1,279 | as "Muse Spark 1.1" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
Vision Arena | #25 | GPT-5.2 | 1,278 | as "GPT-5.2 Chat (20260210)" | captured 2026-11-08 | https://arena.ai/leaderboard/vision
WebDev Arena | #1 | Claude Opus 5.5 | 1,814 | as "Claude Opus 5.5 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #2 | Claude Sonnet 5.5 | 1,772 | as "Claude Sonnet 5.5 (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #3 | GPT-6 Astra | 1,770 | as "GPT-6 Astra (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #4 | Gemini 4 Carbon | 1,767 | as "Gemini 4 Carbon (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #5 | Claude Fable 5.1 | 1,746 | as "Claude Fable 5.1 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #6 | GPT-6.1 Sol | 1,742 | as "GPT-6.1 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #7 | Muse Wonder Full | 1,726 | as "Muse Wonder Full (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #8 | Claude Opus 5 | 1,691 | as "Claude Opus 5 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #9 | Kimi K3.1 Pro | 1,684 | as "Kimi K3.1 Pro (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #10 | Gemini 4 Argon | 1,683 | as "Gemini 4 Argon (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #11 | GPT-6.1 Terra | 1,680 | as "GPT-6.1 Terra (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #12 | Qwen3.8 Max (0902) | 1,677 | as "Qwen3.8-Max (0902)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #13 | GPT-6 Sol | 1,674 | as "GPT-6 Sol (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #14 | DeepSeek V4.1 Flash | 1,665 | as "DeepSeek-V4.1-Flash-20261017 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #15 | Kimi K3 | 1,657 | as "Kimi K3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #16 | Muse Spark 1.3 | 1,654 | as "Muse Spark 1.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #17 | Muse Wonder | 1,649 | as "Muse Wonder (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #18 | Inkling 2 Small | 1,648 | as "Inkling 2 Small" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #19 | Grok 4.7 | 1,638 | as "Grok 4.7 (xHigh)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #20 | MiMo-V2.6-Flash | 1,636 | as "MiMo-V2.6-Flash" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #21 | Hy4 preview | 1,631 | as "Hy4 preview" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #22 | Qwen3.8-Flash-Next | 1,625 | as "Qwen3.8-Flash-Next" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #23 | Claude Fable 5 | 1,625 | as "Claude Fable 5 (High)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #24 | MiMo-V2.6-Pro | 1,624 | as "MiMo-V2.6-Pro" | captured 2026-11-08 | https://arena.ai/leaderboard/code
WebDev Arena | #25 | GLM-5.3 | 1,621 | as "GLM-5.3 (Max)" | captured 2026-11-08 | https://arena.ai/leaderboard/code
MMLU-Pro | #1 | Gemini 3.1 Pro Preview | 91.2% | as "Gemini-3.1-Pro" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #2 | Gemini 3 Pro | 90.1% | as "Gemini-3-Pro(11/25)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #3 | o1 | 89.3% | as "GPT-o1" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #4 | Claude Opus 4.6 | 89.1% | as "Claude-4.6-Opus(Thinking)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #5 | Gemini 3 Flash | 88.6% | as "Gemini-3-Flash(12/25)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #6 | MiniMax M2.1 | 88.0% | as "MiniMax-M2.1" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #7 | Qwen3.5 397B A17B | 87.8% | as "Qwen3.5-397B-A17B" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #8 | Seed2.0 Lite | 87.7% | as "Seed2.0-Lite" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #9 | GPT-5.4 | 87.5% | as "GPT-5.4" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #10 | Claude Sonnet 4.5 | 87.4% | as "Claude-4.5-Sonnet(Thinking)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #10 | GPT-5.2 | 87.4% | as "GPT-5.2" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #12 | Claude Opus 4 | 87.3% | as "Claude-4-Opus-Thinking" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #12 | Claude Opus 4.5 | 87.3% | as "Claude-4.5-Opus(Thinking)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #12 | Claude Sonnet 4.6 | 87.3% | as "Claude-4.6-Sonnet(Thinking)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #15 | Hunyuan T1 | 87.2% | as "Hunyuan-T1" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #16 | GPT-5 | 87.1% | as "GPT-5(high)" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #16 | K2.5 1t A32B | 87.1% | as "K2.5-1T-A32B" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #18 | Grok 4 | 87.0% | as "Grok-4" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #18 | Seed V1.5 | 87.0% | as "Seed-Thinking-v1.5" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #18 | Seed2.0 Pro | 87.0% | as "Seed2.0-Pro" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #21 | Qwen3.5 122B A10B | 86.7% | as "Qwen3.5-122B-A10B" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #22 | Seed1.6 | 86.6% | as "Seed1.6-Thinking" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #22 | Seed1.6 Base | 86.6% | as "Seed1.6-Base" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #24 | GPT-5.1 | 86.4% | as "GPT-5.1" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MMLU-Pro | #24 | Seed1.6 Ada | 86.4% | as "Seed1.6-Ada-Thinking" | captured 2026-11-09 | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
MTEB | #1 | harrier-oss-v1-27b (microsoft) | 74.3% | as "microsoft/harrier-oss-v1-27b" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #2 | KaLM-Embedding-Gemma3-12B-2511 (tencent) | 72.3% | as "tencent/KaLM-Embedding-Gemma3-12B-2511" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #3 | llama-embed-nemotron-8b (nvidia) | 69.5% | as "nvidia/llama-embed-nemotron-8b" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #4 | Qwen3-Embedding-8B (Qwen) | 70.6% | as "Qwen/Qwen3-Embedding-8B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #5 | gemini-embedding-001 (google) | 68.4% | as "google/gemini-embedding-001" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #6 | Qwen3-Embedding-4B (Qwen) | 69.5% | as "Qwen/Qwen3-Embedding-4B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #7 | Octen-Embedding-8B (Octen) | 67.8% | as "Octen/Octen-Embedding-8B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #8 | F2LLM-v2-14B (codefuse-ai) | 68.7% | as "codefuse-ai/F2LLM-v2-14B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #9 | F2LLM-v2-8B (codefuse-ai) | 68.1% | as "codefuse-ai/F2LLM-v2-8B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #10 | harrier-oss-v1-0.6b (microsoft) | 69.0% | as "microsoft/harrier-oss-v1-0.6b" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #11 | Seed1.6-embedding-1215 (Bytedance) | 70.3% | as "Bytedance/Seed1.6-embedding-1215" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #12 | F2LLM-v2-4B (codefuse-ai) | 67.1% | as "codefuse-ai/F2LLM-v2-4B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #13 | Giga-Embeddings-instruct-10B-A1.8B-0826 (ai-sage) | 65.6% | as "ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #14 | jina-embeddings-v5-omni-small (jinaai) | 67.0% | as "jinaai/jina-embeddings-v5-omni-small" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #15 | F2LLM-v2-1.7B (codefuse-ai) | 65.2% | as "codefuse-ai/F2LLM-v2-1.7B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #16 | BidirLM-Omni-2.5B-Embedding (BidirLM) | 63.5% | as "BidirLM/BidirLM-Omni-2.5B-Embedding" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #17 | Giga-Embeddings-instruct-3B-0826 (ai-sage) | 63.9% | as "ai-sage/Giga-Embeddings-instruct-3B-0826" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #18 | harrier-oss-v1-270m (microsoft) | 66.5% | as "microsoft/harrier-oss-v1-270m" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #19 | Qwen3-Embedding-0.6B (Qwen) | 64.3% | as "Qwen/Qwen3-Embedding-0.6B" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #20 | jina-embeddings-v5-omni-nano (jinaai) | 65.5% | as "jinaai/jina-embeddings-v5-omni-nano" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #20 | jina-embeddings-v5-text-nano (jinaai) | 65.5% | as "jinaai/jina-embeddings-v5-text-nano" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #22 | gte-Qwen2-7B-instruct (Alibaba-NLP) | 62.5% | as "Alibaba-NLP/gte-Qwen2-7B-instruct" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #23 | BidirLM-1.7B-Embedding (BidirLM) | 63.5% | as "BidirLM/BidirLM-1.7B-Embedding" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #24 | ICT-TIME-and-Querit-embedding-v1 (ICT-TIME-and-Querit) | 63.8% | as "ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
MTEB | #25 | multilingual-e5-large-instruct (intfloat) | 63.2% | as "intfloat/multilingual-e5-large-instruct" | captured 2026-11-09 | https://huggingface.co/spaces/mteb/leaderboard
Open ASR | #1 | scribe v2.1 pro (zoom) | 4.87 WER | as "zoom/scribe_v2.1_pro" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #2 | speech-v3.1 (OtterAI) | 5.21 WER | as "OtterAI/speech-v3.1" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #3 | azure-speech-09-2026 (microsoft) | 5.55 WER | as "microsoft/azure-speech-09-2026" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #4 | audrey-0.7 (p99lab) | 5.70 WER | as "p99lab/audrey-0.7" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #5 | scribe v2 (elevenlabs) | 5.93 WER | as "elevenlabs/scribe_v2" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #6 | multilingual (modulate) | 5.96 WER | as "modulate/multilingual" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #7 | resonant-1 (reson8) | 5.99 WER | as "reson8/resonant-1" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #8 | asr-k1 (sophea) | 6.11 WER | as "sophea/asr-k1" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #9 | NVIDIA-Nemotron-3.5-Transcribe-30B-A4B (nvidia) | 6.13 WER | as "nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #10 | Qwen3-ASR-1.7B-hf (Qwen) | 6.15 WER | as "Qwen/Qwen3-ASR-1.7B-hf" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #11 | universal-3-5-pro (assemblyai) | 6.21 WER | as "assemblyai/universal-3-5-pro" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #12 | pulse (smallestai) | 6.57 WER | as "smallestai/pulse" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #13 | granite-speech-5.0-2b (ibm-granite) | 6.68 WER | as "ibm-granite/granite-speech-5.0-2b" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #14 | cohere-transcribe-03-2026 (CohereLabs) | 6.72 WER | as "CohereLabs/cohere-transcribe-03-2026" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #15 | Hojo-ASR-V1 (HojoAI) | 6.74 WER | as "HojoAI/Hojo-ASR-V1" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #15 | thewhisper-large-v3-turbo (TheStageAI) | 6.74 WER | as "TheStageAI/thewhisper-large-v3-turbo" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #17 | ARK-ASR-0.6B (Edge0) | 6.75 WER | as "Edge0/ARK-ASR-0.6B" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #18 | gpt-transcribe (openai) | 6.80 WER | as "openai/gpt-transcribe" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #19 | symphony (sprag) | 6.85 WER | as "sprag/symphony" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #20 | solaria-3 (gladia) | 6.86 WER | as "gladia/solaria-3" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #21 | parakeet-tdt-0.6b-v2 (fast-gpu-asr) (nvidia) | 6.91 WER | as "nvidia/parakeet-tdt-0.6b-v2 (fast-gpu-asr)" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #21 | MOSS-Transcribe-Diarize (OpenMOSS-Team) | 6.91 WER | as "OpenMOSS-Team/MOSS-Transcribe-Diarize" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #23 | ARK-ASR-3B (Edge0) | 6.92 WER | as "Edge0/ARK-ASR-3B" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #23 | canary-qwen-2.5b (nvidia) | 6.92 WER | as "nvidia/canary-qwen-2.5b" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Open ASR | #25 | parakeet-tdt-0.6b-v2 (nvidia) | 6.93 WER | as "nvidia/parakeet-tdt-0.6b-v2" | captured 2026-11-09 | https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
OpenRouter | #1 | DeepSeek V4.1 Flash | 56.0T tok | as "deepseek/deepseek-v4.1-flash-20261017" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #2 | GLM 5.3 Flash | 13.2T tok | as "z-ai/glm-5.3-flash-20260826" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #3 | Hy4 preview | 12.8T tok | as "tencent/hy4-20261104" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #4 | GPT-6 Luna | 7.2T tok | as "openai/gpt-6-luna-20260922" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #5 | Step 5 Preview | 7.2T tok | as "stepfun/step-5-preview-20261008" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #6 | Claude Opus 5.5 | 6.8T tok | as "anthropic/claude-opus-5.5-20260921" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #7 | MiniMax-M3.1-Flash | 5.0T tok | as "minimax/minimax-m3.1-flash-20261019" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #8 | Kimi K3.1 Pro | 4.4T tok | as "moonshotai/kimi-k3.1-pro-20261023" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #9 | Crouton Alpha | 4.3T tok | as "stealth/crouton-alpha" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #10 | GPT-6.1 Sol | 4.0T tok | as "openai/gpt-6.1-sol-20260929" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #11 | GLM-5.3 | 3.6T tok | as "z-ai/glm-5.3-20260816" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #12 | DeepSeek V4 Flash Vision | 3.3T tok | as "deepseek/deepseek-v4-flash-20260731" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #13 | Jev 1.13 | 3.1T tok | as "typesafe/jev-1.13-20260917" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #14 | Nemotron 3 Ultra 550B A55B | 3.0T tok | as "nvidia/nemotron-3-ultra-550b-a55b-20260604" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #15 | Nemotron 3.5 Super VL | 2.9T tok | as "nvidia/nemotron-3.5-super-vl-20261015" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #16 | Muse Spark 1.3 Contributor | 2.8T tok | as "meta/muse-spark-1.3-contributor-20260902" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #17 | GPT-5.6 Luna | 2.7T tok | as "openai/gpt-5.6-luna-20260709" | captured 2026-11-09 | https://openrouter.ai/rankings
OpenRouter | #18 | Claude Haiku 5.5 | 2.7T tok | as "anthropic/claude-haiku-5.5-20261007" | captured 2026-11-09 | https://openrouter.ai/rankings
HLE | #1 | GPT-6 Astra | 54.8% | as "GPT 6 Astra" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #2 | Claude Fable 5.1 | 46.5% | as "Fable 5.1 (xhigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #3 | Gemini 3.1 Pro Preview | 46.4% | as "gemini-3.1-pro-preview (thinking high)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #4 | Claude Sonnet 5.5 | 46.1% | as "Sonnet 5.5 (xhigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #5 | Gemini 3.8 Flash | 44.5% | as "Gemini 3.8 Flash" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #6 | GPT-5.4 Pro | 44.3% | as "gpt-5.4-pro-2026-03-05" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #7 | Muse Spark | 40.6% | as "Muse Spark" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #8 | Gemini 3 Pro | 37.5% | as "gemini-3-pro-preview" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #9 | GPT-5.4 | 36.2% | as "gpt-5.4-2026-03-05 (xhigh thinking)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #10 | Claude Opus 4.7 | 36.2% | as "claude-opus-4-7" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #11 | Claude Opus 4.6 | 34.4% | as "claude-opus-4-6-thinking-max" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #12 | GPT-5 Pro | 31.6% | as "gpt-5-pro-2025-10-06" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #13 | Claude Haiku 5.5 | 30.1% | as "Claude Haiku 5.5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #14 | GPT-5.2 | 27.8% | as "gpt-5.2-2025-12-11" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #15 | GPT-5 | 25.3% | as "gpt-5-2025-08-07" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #16 | Claude Opus 4.5 | 25.2% | as "claude-opus-4-5-20251101-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #17 | Kimi K2.5 | 24.4% | as "kimi-k2.5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #18 | GPT-5.1 | 23.7% | as "gpt-5.1-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #19 | Gemini 2.5 Pro (Jun 2025) | 21.6% | as "gemini-2.5-pro-preview-06-05" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #20 | o3 | 20.3% | as "o3 (high) (April 2025)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #21 | GPT-5 mini | 19.4% | as "gpt-5-mini-2025-08-07" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #22 | o4-mini | 18.1% | as "o4-mini (high) (April 2025)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #23 | Claude Sonnet 4.5 | 13.7% | as "claude-sonnet-4-5-20250929-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #24 | Gemini 2.5 Flash (Sep 2025) | 12.1% | as "Gemini 2.5 Flash (April 2025)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
HLE | #25 | Claude Opus 4.1 | 11.5% | as "claude-opus-4-1-20250805-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/humanitys_last_exam
MCP Atlas | #1 | Gemini 4 Argon | 90.7% | as "Gemini-4-Argon" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #2 | Muse Spark 1.1 | 88.1% | as "Muse Spark 1.1" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #3 | Claude Fable 5.1 | 87.2% | as "Fable 5.1" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #4 | Claude Opus 5 | 85.8% | as "claude-opus-5 (xhigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #5 | Claude Opus 5.5 | 85.4% | as "Opus 5.5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #5 | Inkling Small 2 | 85.4% | as "Inkling Small 2" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #7 | Qwen3.8 2.4T A95B | 84.5% | as "Qwen3.8-2.4T-A95B (xHigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #8 | GLM-5.3 | 84.2% | as "GLM 5.3" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #9 | Gemini 3.5 Flash | 83.6% | as "Gemini 3.5 Flash (high)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #10 | Claude Fable 5 | 83.3% | as "Claude Fable 5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #11 | Kimi K3 | 82.3% | as "kimi-k3 (max)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #12 | Claude Opus 4.8 | 82.2% | as "claude-opus-4-8 (max)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #12 | Muse Spark | 82.2% | as "Muse Spark" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #14 | GPT-5.6 | 81.8% | as "gpt-5.6 (sol)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #15 | Inkling Small | 79.2% | as "Inkling-small" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #16 | Claude Opus 4.7 | 79.1% | as "claude-opus-4-7 (max)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #17 | Gemini 3.1 Pro Preview | 78.2% | as "gemini-3.1-pro-preview (high)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #18 | GLM-5p2 | 77.8% | as "glm-5p2" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #19 | Claude Opus 4.6 | 76.8% | as "claude-opus-4-6 (max)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #20 | Inkling | 76.0% | as "Inkling (xHigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #21 | GLM-5p1 | 75.6% | as "glm-5p1" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #22 | GPT-5.5 | 75.3% | as "gpt-5.5 (xhigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #23 | GPT-5.4 | 70.6% | as "gpt-5.4 (xhigh)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #24 | Gemini 3 Pro | 70.3% | as "gemini-3-pro-preview" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MCP Atlas | #25 | Claude Opus 4.5 | 69.8% | as "claude-opus-4-5 (high)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/mcp_atlas
MultiChallenge | #1 | GPT-6.1 Sol | 82.0% | as "gpt 6.1 Sol" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #2 | Gemini 4 Argon | 78.7% | as "Gemini 4 Argon" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #3 | Muse Spark | 75.5% | as "Muse Spark" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #4 | Muse Spark 1.1 | 75.3% | as "Muse Spark 1.1" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #5 | DeepSeek V4P1 Flash | 74.9% | as "Deepseek V4p1 Flash 1017" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #6 | GPT-6.1 Terra | 74.2% | as "GPT 6.1 Terra" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #6 | Muse Spark Open | 74.2% | as "Muse Spark Open" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #8 | Gemini 3.1 Pro Preview | 71.4% | as "gemini-3.1-pro-preview" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #9 | GPT-5.4 Pro | 69.2% | as "gpt-5.4-pro-2026-03-05" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #10 | Claude Haiku 5.5 | 67.7% | as "Claude Haiku 5.5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #11 | Gemini 3 Pro | 65.7% | as "gemini-3-pro-preview" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #12 | GPT-5.1 | 63.4% | as "gpt-5.1-2025-11-13-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #13 | GPT-5 | 63.2% | as "gpt-5-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #14 | o3-pro | 62.4% | as "o3-pro-2025-06-10-reasoning-high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #15 | Kimi K2.5 | 61.4% | as "kimi-k2.5" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #16 | Gemini 3.1 Flash-Lite | 60.6% | as "gemini-3.1-flash-lite-preview" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #17 | GPT-5 mini | 59.0% | as "gpt-5-mini-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #18 | Claude Opus 4.5 | 59.0% | as "claude-opus-4-5-20251101-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #19 | Claude Opus 4 | 58.6% | as "claude-4-opus-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #20 | Claude Opus 4.1 | 57.2% | as "claude-opus-4-1-20250805-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #21 | Claude Sonnet 4 | 57.1% | as "claude-4-sonnet-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #22 | o3 | 56.6% | as "o3-2025-04-16-reasoning-high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #23 | Claude Opus 4.6 | 56.0% | as "claude-opus-4-6 (Non-Thinking)" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #24 | Kimi K2 Thinking | 55.4% | as "kimi-k2-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
MultiChallenge | #25 | Claude Sonnet 4.5 | 55.3% | as "claude-sonnet-4-5-20250929-thinking" | captured 2026-11-09 | https://labs.scale.com/leaderboard/multichallenge
SWE-Bench Pro | #1 | Claude Opus 5 | 98.0% | as "Opus 5 (Claude Code) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #2 | Claude Fable 5.1 | 92.2% | as "Fable 5.1 (Claude Code) high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #3 | Gemini 4 Argon | 92.2% | as "Gemini 4 Argon (mini-swe-agent) high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #4 | GPT-6 Astra | 90.2% | as "GPT-6 Astra (Codex) high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #4 | Muse Wonder 1.0 Max Effort | 90.2% | as "Muse Wonder 1.0 (mini-swe-agent) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #6 | Claude Sonnet 5 | 88.2% | as "Sonnet 5 (Claude Code) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #6 | Kimi K3 | 88.2% | as "Kimi-K3 (mini-swe-agent) max" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #8 | GPT-5.6 Terra | 86.3% | as "GPT-5.6 Terra (Codex) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #9 | Inkling Small 2 | 86.3% | as "Inkling Small 2" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #10 | MiniMax M3P1 Flash | 84.3% | as "Minimax M3p1 Flash (mini-swe-agent) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #11 | GLM-5.3 | 84.3% | as "GLM-5.3 (mini-swe-agent) max" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #12 | GPT-5.6 Sol | 82.4% | as "GPT-5.6 Sol (Codex) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #13 | Muse Spark Open | 82.3% | as "Muse Spark Open (mini-swe-agent) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #14 | Claude Sonnet 5.5 | 70.6% | as "Sonnet 5.5 (mini-swe-agent) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #15 | Gemini 3.8 Flash | 58.8% | as "Gemini 3.8 Flash (mini-swe-agent) high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #16 | Inkling | 56.9% | as "Inkling (mini-swe-agent) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #17 | Claude Haiku 5.5 | 52.9% | as "Haiku 5.5 (mini-swe-agent) high" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-Bench Pro | #18 | Claude 4.5 Haiku | 25.5% | as "Haiku 4.5 (Claude Code) xhigh" | captured 2026-11-09 | https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
SWE-bench Verified | #1 | Claude Opus 4.5 | 76.8% | as "Claude 4.5 Opus (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #2 | Gemini 3 Flash | 75.8% | as "Gemini 3 Flash (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #2 | MiniMax-M2.5 | 75.8% | as "MiniMax M2.5 (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #4 | Claude Opus 4.6 | 75.6% | as "Claude 4.6 Opus" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #5 | Gemini 3 Pro | 74.2% | as "Gemini 3 Pro Preview (2025-11-18)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #6 | GLM-5 | 72.8% | as "GLM 5 (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #6 | GPT-5.2 | 72.8% | as "GPT 5.2 (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #6 | GPT-5.2 Codex | 72.8% | as "GPT 5.2 Codex" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #9 | Claude Sonnet 4.5 | 71.4% | as "Claude 4.5 Sonnet (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #10 | Kimi K2.5 | 70.8% | as "Kimi K2.5 (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #11 | DeepSeek-V3.2 | 70.0% | as "DeepSeek V3.2 (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #12 | Claude Opus 4 | 67.6% | as "Claude 4 Opus (20250514)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #13 | Claude 4.5 Haiku | 66.6% | as "Claude 4.5 Haiku (high)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #14 | GPT-5.1 | 66.0% | as "GPT 5.1 (2025-11-13) (medium)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #14 | GPT 5.1 Codex | 66.0% | as "GPT 5.1 Codex (medium)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #16 | GPT-5 | 65.0% | as "GPT 5 (2025-08-07) (medium)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #17 | Claude Sonnet 4 | 64.9% | as "Claude 4 Sonnet (20250514)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #18 | Kimi K2 Thinking | 63.4% | as "Kimi K2 Thinking" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #19 | MiniMax M2 | 61.0% | as "MiniMax M2" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #20 | GPT-5 mini | 59.8% | as "GPT 5 mini (2025-08-07) (medium)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #21 | o3 | 58.4% | as "o3 (2025-04-16)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #22 | Devstral Small (2512) | 56.4% | as "Devstral Small (2512)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #23 | GLM 4.6 | 55.4% | as "GLM 4.6 (T=1)" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #23 | Qwen3-Coder 480B/A35B Instruct | 55.4% | as "Qwen3-Coder 480B/A35B Instruct" | captured 2026-11-09 | https://www.swebench.com/
SWE-bench Verified | #25 | GLM 4.5 | 54.2% | as "GLM 4.5 (2025-08-22)" | captured 2026-11-09 | https://www.swebench.com/