Leaderboard changes: who moved, entered, left

Nov 11, 2026300 changes

SpeedArtificial Analysis Output SpeedArtificial Analysis Output SpeedNew version published (2026-11-07 to 2026-11-11)

SpeedArtificial Analysis Output SpeedTencent Hy4Left the top 100, was #23.

SpeedArtificial Analysis Output SpeedClaude Fable 5.1Left the top 100, was #14.

SpeedArtificial Analysis Output SpeedMistral Small 4Fell from #43 to #45.

SpeedArtificial Analysis Output SpeedGemini 3.5 Flash-LiteFell from #42 to #45.

SpeedArtificial Analysis Output SpeedBeam 1.0Fell from #41 to #44.

SpeedArtificial Analysis Output SpeedNorth Mini CodeFell from #39 to #42.

SpeedArtificial Analysis Output SpeedCommand A+Fell from #40 to #42.

SpeedArtificial Analysis Output SpeedMuse EmberEntered at #41.

SpeedArtificial Analysis Output SpeedNemotron 3.5 LightningFell from #38 to #39.

SpeedArtificial Analysis Output SpeedNemotron 3 UltraFell from #33 to #39.

SpeedArtificial Analysis Output SpeedMistral Medium 3.5Fell from #36 to #38.

SpeedArtificial Analysis Output SpeedMuse GlimmerScore 4.60 to 4.90, still #37.

SpeedArtificial Analysis Output SpeedNemotron 3.5 Super VLFell from #31 to #36.

SpeedArtificial Analysis Output SpeedK2 Horizon 375B A23BScore 4.90 to 5.60, still #35.

SpeedArtificial Analysis Output SpeedMuse Spark OpenFell from #32 to #34.

SpeedArtificial Analysis Output Speedgpt-oss-120bEntered at #33.

SpeedArtificial Analysis Output SpeedInkling SmallRose from #34 to #32.

SpeedArtificial Analysis Output SpeedInklingFell from #30 to #31.

SpeedArtificial Analysis Output SpeedGranite 4.2 8BFell from #26 to #30.

SpeedArtificial Analysis Output SpeedGPT-6 LunaFell from #28 to #29.

SpeedArtificial Analysis Output SpeedMistral Large 4 HighFell from #21 to #28.

SpeedArtificial Analysis Output SpeedMiniMax-M3Score 13.1 to 12.3, still #27.

SpeedArtificial Analysis Output SpeedStep 5 PreviewFell from #22 to #25.

SpeedArtificial Analysis Output SpeedMuse WonderRose from #29 to #25.

SpeedArtificial Analysis Output SpeedApodex 1.1Entered at #24.

SpeedArtificial Analysis Output SpeedGPT-6.1 TerraRose from #24 to #23.

SpeedArtificial Analysis Output SpeedGemini 3.8 FlashFell from #20 to #22.

SpeedArtificial Analysis Output SpeedMiniMax-M3.1-FlashFell from #17 to #21.

SpeedArtificial Analysis Output SpeedClaude Haiku 5.5Fell from #19 to #20.

SpeedArtificial Analysis Output SpeedDeepSeek V4.1 FlashRose from #25 to #19.

SpeedArtificial Analysis Output SpeedInkling 2 SmallScore 16.5 to 19.6, still #18.

SpeedArtificial Analysis Output SpeedGPT-6.1 SolFell from #15 to #17.

SpeedArtificial Analysis Output SpeedGPT-6 AstraScore 20.9 to 23, still #16.

SpeedArtificial Analysis Output SpeedDeepSeek V4 Pro 0813Fell from #13 to #15.

SpeedArtificial Analysis Output SpeedAgnes 2.5 Pro ThetaEntered at #14.

SpeedArtificial Analysis Output SpeedClaude Opus 5.5Fell from #11 to #13.

SpeedArtificial Analysis Output SpeedGemini 4 CarbonFell from #7 to #12.

SpeedArtificial Analysis Output SpeedGrok 4.7Rose from #12 to #11.

SpeedArtificial Analysis Output SpeedGemini 4 ArgonScore 27.7 to 28.6, still #10.

SpeedArtificial Analysis Output SpeedGLM-5.3Fell from #8 to #9.

SpeedArtificial Analysis Output SpeedClaude Sonnet 5.5Rose from #9 to #8.

SpeedArtificial Analysis Output SpeedMiMo-V2.6-ProFell from #4 to #7.

SpeedArtificial Analysis Output SpeedKimi K3.1 ProScore 36.1 to 37.1, still #6.

SpeedArtificial Analysis Output SpeedQwen3.8 27BFell from #3 to #5.

SpeedArtificial Analysis Output SpeedClaude Fable 5.2Entered at #4.

SpeedArtificial Analysis Output SpeedGLM 5.3 FlashRose from #5 to #3.

SpeedArtificial Analysis Output SpeedQwen3.8 Max (0902)Score 60.2 to 55.8, still #2.

SpeedArtificial Analysis Output SpeedMiMo-V2.6-FlashScore 64 to 62.6, still #1.

UsageOpenRouter weekly usageOpenRouter weekly usageNew version published (2026-11-09 to 2026-11-10)

UsageOpenRouter weekly usageClaude Sonnet 5.5Score 2380.6 to 2389.9, still #19.

UsageOpenRouter weekly usageClaude Haiku 5.5Fell from #17 to #18.

UsageOpenRouter weekly usageMiMo-V2.6-FlashRose from #18 to #17.

UsageOpenRouter weekly usageNemotron 3.5 Super VLScore 2858.6 to 2874.7, still #16.

UsageOpenRouter weekly usageMuse Spark 1.3 ContributorScore 2873.9 to 2892.1, still #15.

UsageOpenRouter weekly usageJev 1.13Score 3032.6 to 2899.0, still #14.

UsageOpenRouter weekly usageDeepSeek V4 Flash VisionFell from #12 to #13.

UsageOpenRouter weekly usageNemotron 3 Ultra 550B A55BRose from #13 to #12.

UsageOpenRouter weekly usageGLM-5.3Score 3575.5 to 3646.9, still #11.

UsageOpenRouter weekly usageGPT-6.1 SolScore 3924.8 to 4085.1, still #10.

UsageOpenRouter weekly usageMiniMax-M3.1-FlashFell from #8 to #9.

UsageOpenRouter weekly usageKimi K3.1 ProRose from #9 to #8.

UsageOpenRouter weekly usageCrouton AlphaScore 5099.3 to 5074.1, still #7.

UsageOpenRouter weekly usageClaude Opus 5.5Score 6745.0 to 6760.9, still #6.

UsageOpenRouter weekly usageStep 5 PreviewFell from #4 to #5.

UsageOpenRouter weekly usageGPT-6 LunaRose from #5 to #4.

UsageOpenRouter weekly usageGLM 5.3 FlashScore 12143.3 to 11279.9, still #3.

UsageOpenRouter weekly usageHy4 previewScore 15981.6 to 18808.2, still #2.

UsageOpenRouter weekly usageDeepSeek V4.1 FlashScore 55448.8 to 53751.9, still #1.

SpeechOpen ASR LeaderboardOpen ASR LeaderboardNew version published (2026-11-09 to 2026-11-10)

SpeechOpen ASR Leaderboardresonant-1 (reson8)Left the top 100, was #7.

SpeechOpen ASR Leaderboardniagara-9m-batch.en (abr-ai)Fell from #62 to #63.

SpeechOpen ASR Leaderboardniagara-19m-batch.en (abr-ai)Fell from #61 to #62.

SpeechOpen ASR Leaderboardasr4all-s (futo-org)Fell from #60 to #61.

SpeechOpen ASR LeaderboardomniASR-CTC-7B-v2 (facebook)Fell from #59 to #60.

SpeechOpen ASR Leaderboardgemma-4-E4B-it (google)Fell from #58 to #59.

SpeechOpen ASR Leaderboardniagara-38m-batch.en (abr-ai)Fell from #57 to #58.

SpeechOpen ASR Leaderboardasr4all-m (futo-org)Fell from #56 to #57.

SpeechOpen ASR Leaderboardnemotron-3.5-asr-streaming-0.6b (nvidia)Fell from #55 to #56.

SpeechOpen ASR Leaderboardniagara-84m-batch.en (abr-ai)Fell from #54 to #55.

SpeechOpen ASR Leaderboardasr4all-l (futo-org)Fell from #53 to #54.

SpeechOpen ASR LeaderboardVoxtral-Mini-4B-Realtime-2602 (mistralai)Fell from #52 to #53.

SpeechOpen ASR LeaderboardVibeVoice-ASR-HF (microsoft)Fell from #51 to #52.

SpeechOpen ASR LeaderboardomniASR-LLM-7B-v2 (facebook)Fell from #50 to #51.

SpeechOpen ASR LeaderboardAudio8-ASR-0.1B (Edge0)Fell from #49 to #50.

SpeechOpen ASR Leaderboardowsm ctc v4 1B (espnet)Fell from #48 to #49.

SpeechOpen ASR Leaderboardwhisper-large-v3-turbo (openai)Fell from #47 to #48.

SpeechOpen ASR LeaderboardLuciole-8B-Audio-1.0 (OpenLLM-France)Fell from #46 to #47.

SpeechOpen ASR LeaderboardFun-ASR-Nano-2512-hf (FunAudioLLM)Fell from #45 to #46.

SpeechOpen ASR Leaderboardcanary-1b-v2 (nvidia)Fell from #44 to #45.

SpeechOpen ASR LeaderboardVoxtral-Mini-3B-2507 (mistralai)Fell from #43 to #44.

SpeechOpen ASR Leaderboardwhisper-large-v3 (openai)Fell from #42 to #43.

SpeechOpen ASR LeaderboardZipformer-cr-ctc-transducer-XL-290M (fast-gpu-asr, transducer modified beam search) (soundsgoodai)Fell from #41 to #42.

SpeechOpen ASR LeaderboardPhonon-2 (FermionResearch)Fell from #40 to #41.

SpeechOpen ASR Leaderboardgranite-4.0-1b-speech (ibm-granite)Fell from #39 to #40.

SpeechOpen ASR Leaderboarddistil-large-v3.5 (distil-whisper)Fell from #38 to #39.

SpeechOpen ASR Leaderboardnemotron-speech-streaming-en-0.6b (nvidia)Fell from #37 to #38.

SpeechOpen ASR LeaderboardVoxtral-Small-24B-2507 (mistralai)Fell from #36 to #37.

SpeechOpen ASR Leaderboardgranite-speech-5.0-470m-turboctc (ibm-granite)Fell from #35 to #36.

SpeechOpen ASR Leaderboardgranite-speech-4.1-2b-nar (ibm-granite)Fell from #34 to #35.

SpeechOpen ASR LeaderboardQwen3-ASR-0.6B-hf (Qwen)Fell from #33 to #34.

SpeechOpen ASR Leaderboardkapture-v3 (fonada)Fell from #32 to #33.

SpeechOpen ASR Leaderboardparakeet-tdt-0.6b-v3 (nvidia)Fell from #31 to #32.

SpeechOpen ASR Leaderboardgranite-speech-4.1-2b (ibm-granite)Fell from #30 to #31.

SpeechOpen ASR Leaderboardmuse-voice-transcribe (meta)Fell from #29 to #30.

SpeechOpen ASR Leaderboardgranite-speech-5.0-470m-turboctc-nc (ibm-granite)Fell from #27 to #28.

SpeechOpen ASR Leaderboardhiggs-audio-v3-stt (bosonai)Fell from #27 to #28.

SpeechOpen ASR Leaderboardparakeet-tdt-0.6b-v3 (fast-gpu-asr) (nvidia)Fell from #26 to #27.

SpeechOpen ASR Leaderboardparakeet-tdt-0.6b-v2 (nvidia)Fell from #25 to #26.

SpeechOpen ASR LeaderboardARK-ASR-3B (Edge0)Fell from #23 to #24.

SpeechOpen ASR Leaderboardcanary-qwen-2.5b (nvidia)Fell from #23 to #24.

SpeechOpen ASR LeaderboardMOSS-Transcribe-Diarize (OpenMOSS-Team)Fell from #21 to #22.

SpeechOpen ASR Leaderboardparakeet-tdt-0.6b-v2 (fast-gpu-asr) (nvidia)Fell from #21 to #22.

SpeechOpen ASR Leaderboardsolaria-3 (gladia)Fell from #20 to #21.

SpeechOpen ASR Leaderboardsymphony (sprag)Fell from #19 to #20.

SpeechOpen ASR Leaderboardgpt-transcribe (openai)Fell from #18 to #19.

SpeechOpen ASR LeaderboardARK-ASR-0.6B (Edge0)Fell from #17 to #18.

SpeechOpen ASR LeaderboardHojo-ASR-V1 (HojoAI)Fell from #15 to #16.

SpeechOpen ASR Leaderboardthewhisper-large-v3-turbo (TheStageAI)Fell from #15 to #16.

SpeechOpen ASR Leaderboardcohere-transcribe-03-2026 (CohereLabs)Fell from #14 to #15.

SpeechOpen ASR Leaderboardgranite-speech-5.0-2b (ibm-granite)Fell from #13 to #14.

SpeechOpen ASR Leaderboardpulse (smallestai)Fell from #12 to #13.

SpeechOpen ASR Leaderboarduniversal-3-5-pro (assemblyai)Fell from #11 to #12.

SpeechOpen ASR LeaderboardQwen3-ASR-1.7B-hf (Qwen)Fell from #10 to #11.

SpeechOpen ASR LeaderboardNVIDIA-Nemotron-3.5-Transcribe-30B-A4B (nvidia)Fell from #9 to #10.

SpeechOpen ASR Leaderboardasr-k1 (sophea)Fell from #8 to #9.

SpeechOpen ASR Leaderboardmultilingual (modulate)Fell from #6 to #8.

SpeechOpen ASR Leaderboardrumble-2 (reson8)Entered at #7.

SpeechOpen ASR Leaderboardscribe v2 (elevenlabs)Fell from #5 to #6.

SpeechOpen ASR LeaderboardMusci-ASR-qwen-1019-hf (Musci-research)Entered at #4.

rumble-2 (reson8)New model, first ranked.

Musci-ASR-qwen-1019-hf (Musci-research)New model, first ranked.

ReasoningARC-AGI-2ARC-AGI-2New version published (2026-11-09 to 2026-11-10)

ReasoningARC-AGI-2MagistralFell from #85 to #86.

ReasoningARC-AGI-2Magistral SmallFell from #85 to #86.

ReasoningARC-AGI-2Grok 3Fell from #85 to #86.

ReasoningARC-AGI-2GPT 4.1 miniFell from #85 to #86.

ReasoningARC-AGI-2GPT-4.1 NanoFell from #85 to #86.

ReasoningARC-AGI-2Llama 4 Scout InstructFell from #85 to #86.

ReasoningARC-AGI-2Llama 4 Maverick InstructFell from #85 to #86.

ReasoningARC-AGI-2GPT-4o MiniFell from #85 to #86.

ReasoningARC-AGI-2GPT 4oFell from #85 to #86.

ReasoningARC-AGI-2Grok-3 miniFell from #83 to #84.

ReasoningARC-AGI-2GPT 4.1Fell from #83 to #84.

ReasoningARC-AGI-2GPT-4.5Fell from #81 to #82.

ReasoningARC-AGI-2Gemini 1.5 ProFell from #81 to #82.

ReasoningARC-AGI-2o1 MiniFell from #80 to #81.

ReasoningARC-AGI-2Claude 3.7 SonnetFell from #79 to #80.

ReasoningARC-AGI-2Qwen3-235B-A22B-Thinking (Jul 2025)Fell from #78 to #79.

ReasoningARC-AGI-2Codex MiniFell from #77 to #78.

ReasoningARC-AGI-2DeepSeek-R1 (May 2025)Fell from #75 to #76.

ReasoningARC-AGI-2Gemini 2.0 FlashFell from #75 to #76.

ReasoningARC-AGI-2Nemotron 3.5 Super VLFell from #74 to #75.

ReasoningARC-AGI-2Gemini 2.5 Flash (Sep 2025)Fell from #73 to #74.

ReasoningARC-AGI-2GPT 5 nanoFell from #72 to #73.

ReasoningARC-AGI-2o3 MiniFell from #71 to #72.

ReasoningARC-AGI-2DeepSeek-V3.2Fell from #69 to #70.

ReasoningARC-AGI-2Claude 4.5 HaikuFell from #69 to #70.

ReasoningARC-AGI-2GPT-5 miniFell from #68 to #69.

ReasoningARC-AGI-2GLM-5Fell from #65 to #66.

ReasoningARC-AGI-2MiniMax-M2.5Fell from #65 to #66.

ReasoningARC-AGI-2Gemini 2.5 Pro (Jun 2025)Fell from #65 to #66.

ReasoningARC-AGI-2GPT-5.4 NanoFell from #64 to #65.

ReasoningARC-AGI-2Claude Sonnet 4Fell from #63 to #64.

ReasoningARC-AGI-2o4-miniFell from #62 to #63.

ReasoningARC-AGI-2o3Fell from #61 to #62.

ReasoningARC-AGI-2Claude Opus 4Fell from #60 to #61.

ReasoningARC-AGI-2GPT-5Fell from #59 to #60.

ReasoningARC-AGI-2Gemini 3.5 Flash-LiteFell from #58 to #59.

ReasoningARC-AGI-2Kimi K2.5Fell from #57 to #58.

ReasoningARC-AGI-2Claude Sonnet 4.5Fell from #56 to #57.

ReasoningARC-AGI-2Grok 4Fell from #55 to #56.

ReasoningARC-AGI-2GPT-5.1Fell from #54 to #55.

ReasoningARC-AGI-2GPT-5 ProFell from #53 to #54.

ReasoningARC-AGI-2GPT-5.4 MiniFell from #52 to #53.

ReasoningARC-AGI-2GLM-5.2Fell from #51 to #52.

ReasoningARC-AGI-2Beam 1.0Fell from #50 to #51.

ReasoningARC-AGI-2Gemini 3 ProFell from #49 to #50.

ReasoningARC-AGI-2Gemini 3 FlashFell from #48 to #49.

ReasoningARC-AGI-2InklingFell from #47 to #48.

ReasoningARC-AGI-2Claude Opus 4.5Fell from #46 to #47.

ReasoningARC-AGI-2Inkling SmallFell from #45 to #46.

ReasoningARC-AGI-2Qwen3.8 27BFell from #44 to #45.

ReasoningARC-AGI-2Grok 4.5Fell from #43 to #44.

ReasoningARC-AGI-2GPT-5.2Fell from #42 to #43.

ReasoningARC-AGI-2GPT-5.2 ProFell from #41 to #42.

ReasoningARC-AGI-2Muse Spark OpenFell from #40 to #41.

ReasoningARC-AGI-2GPT-6 LunaFell from #39 to #40.

ReasoningARC-AGI-2GPT-5.6 LunaFell from #38 to #39.

ReasoningARC-AGI-2Gemini 3.6 FlashFell from #36 to #37.

ReasoningARC-AGI-2Kimi K3Fell from #36 to #37.

ReasoningARC-AGI-2Claude Sonnet 4.6Fell from #35 to #36.

ReasoningARC-AGI-2Claude Haiku 5.5Fell from #33 to #34.

ReasoningARC-AGI-2DeepSeek V4 Pro 0813Fell from #33 to #34.

ReasoningARC-AGI-2Grok 4.7Fell from #31 to #32.

ReasoningARC-AGI-2DeepSeek V4 Flash VisionFell from #31 to #32.

ReasoningARC-AGI-2Grok 4.20Fell from #30 to #31.

ReasoningARC-AGI-2GLM 5.3 FlashFell from #29 to #30.

ReasoningARC-AGI-2Grok 4.6Fell from #28 to #29.

ReasoningARC-AGI-2Claude Opus 4.6Fell from #27 to #28.

ReasoningARC-AGI-2Gemini 3.5 FlashFell from #25 to #26.

ReasoningARC-AGI-2Claude Opus 4.8Fell from #25 to #26.

ReasoningARC-AGI-2GPT-5.4Fell from #24 to #25.

ReasoningARC-AGI-2Claude 4.7Fell from #23 to #24.

ReasoningARC-AGI-2Dots3 NoteFell from #22 to #23.

ReasoningARC-AGI-2Gemini 3.1 Pro PreviewFell from #21 to #22.

ReasoningARC-AGI-2DeepSeek V4.1 FlashFell from #20 to #21.

ReasoningARC-AGI-2Inkling 2 SmallFell from #19 to #20.

ReasoningARC-AGI-2GPT-5.4 ProFell from #18 to #19.

ReasoningARC-AGI-2Claude Sonnet 5.5Fell from #17 to #18.

ReasoningARC-AGI-2GPT-5.6 TerraFell from #16 to #17.

ReasoningARC-AGI-2GPT-5.5 ProFell from #14 to #15.

ReasoningARC-AGI-2Gemini 3Fell from #14 to #15.

ReasoningARC-AGI-2Gemini 3.7 FlashFell from #13 to #14.

ReasoningARC-AGI-2GPT-5.5Fell from #12 to #13.

ReasoningARC-AGI-2Gemini 3.8 FlashFell from #10 to #11.

ReasoningARC-AGI-2Claude Fable 5Fell from #10 to #11.

ReasoningARC-AGI-2GPT-6 SolFell from #9 to #10.

ReasoningARC-AGI-2Claude Fable 5.1Fell from #8 to #9.

ReasoningARC-AGI-2Claude Opus 5Fell from #7 to #8.

ReasoningARC-AGI-2Gemini 4 ArgonFell from #6 to #7.

ReasoningARC-AGI-2GPT-5.6 SolFell from #5 to #6.

ReasoningARC-AGI-2Claude Opus 5.5Fell from #4 to #5.

ReasoningARC-AGI-2Claude Fable 5.2Fell from #3 to #4.

ReasoningARC-AGI-2Gemini 4 CarbonEntered at #2.

ReasoningEpoch Capabilities IndexEpoch Capabilities IndexNew version published (2026-11-10 to 2026-11-11)

ReasoningGPQA Diamond (Epoch AI runs)o3 MiniLeft the top 100, was #100.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 4.1Fell from #99 to #100.

ReasoningGPQA Diamond (Epoch AI runs)Seed 1.6Fell from #98 to #99.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.4 NanoFell from #97 to #98.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.5 9BFell from #96 to #97.

ReasoningGPQA Diamond (Epoch AI runs)Claude Sonnet 4Fell from #95 to #96.

ReasoningGPQA Diamond (Epoch AI runs)o4-miniFell from #94 to #95.

ReasoningGPQA Diamond (Epoch AI runs)Claude 3.7 SonnetFell from #93 to #94.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3-235B-A22B-Thinking (Jul 2025)Fell from #92 to #93.

ReasoningGPQA Diamond (Epoch AI runs)o3Fell from #90 to #91.

ReasoningGPQA Diamond (Epoch AI runs)Gemini 3.1 Flash-LiteFell from #90 to #91.

ReasoningGPQA Diamond (Epoch AI runs)Claude Sonnet 4.5Fell from #87 to #88.

ReasoningGPQA Diamond (Epoch AI runs)Qwen 3.5 Flash (hosted 35B-A3B)Fell from #87 to #88.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.7 FlashFell from #87 to #88.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.5 Instant (June 2026)Fell from #86 to #87.

ReasoningGPQA Diamond (Epoch AI runs)GLM-4.7Fell from #83 to #84.

ReasoningGPQA Diamond (Epoch AI runs)Gemini 3.5 Flash-LiteFell from #83 to #84.

ReasoningGPQA Diamond (Epoch AI runs)Qwen 3.6 FlashFell from #83 to #84.

ReasoningGPQA Diamond (Epoch AI runs)DeepSeekFell from #82 to #83.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.5-35B-A3BFell from #81 to #82.

ReasoningGPQA Diamond (Epoch AI runs)Kimi K2 TurboFell from #80 to #81.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.6 35B A3BFell from #78 to #79.

ReasoningGPQA Diamond (Epoch AI runs)Qwen 3.5 Plus (hosted 397B-A17B)Fell from #78 to #79.

ReasoningGPQA Diamond (Epoch AI runs)Gemini 2.5 Pro (Jun 2025)Fell from #77 to #78.

ReasoningGPQA Diamond (Epoch AI runs)Nemotron 3 UltraFell from #76 to #77.

ReasoningGPQA Diamond (Epoch AI runs)Claude Fable 5Fell from #74 to #75.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.6 27BFell from #74 to #75.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 4.5Fell from #73 to #74.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5Fell from #72 to #73.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.5 397B A17BFell from #71 to #72.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.4 MiniFell from #70 to #71.

ReasoningGPQA Diamond (Epoch AI runs)Grok 4Fell from #69 to #70.

ReasoningGPQA Diamond (Epoch AI runs)Claude Sonnet 4.6Fell from #67 to #68.

ReasoningGPQA Diamond (Epoch AI runs)Qwen 3.6 Max (Preview)Fell from #67 to #68.

ReasoningGPQA Diamond (Epoch AI runs)Kimi K2P5Fell from #66 to #67.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.1Fell from #65 to #66.

ReasoningGPQA Diamond (Epoch AI runs)GLM-5Fell from #64 to #65.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.7 PlusFell from #62 to #63.

ReasoningGPQA Diamond (Epoch AI runs)Kimi K2.7 CodeFell from #62 to #63.

ReasoningGPQA Diamond (Epoch AI runs)Mistral Large 4 0Fell from #61 to #62.

ReasoningGPQA Diamond (Epoch AI runs)Doubao Seed 2.0 Lite 260428Fell from #60 to #61.

ReasoningGPQA Diamond (Epoch AI runs)Doubao Seed 2.0 Pro 260215Fell from #59 to #60.

ReasoningGPQA Diamond (Epoch AI runs)InklingFell from #58 to #59.

ReasoningGPQA Diamond (Epoch AI runs)Qwen 3.6 PlusFell from #57 to #58.

ReasoningGPQA Diamond (Epoch AI runs)Inkling SmallFell from #56 to #57.

ReasoningGPQA Diamond (Epoch AI runs)Muse Spark Open 816b A42BFell from #55 to #56.

ReasoningGPQA Diamond (Epoch AI runs)Grok 4.3 BetaFell from #54 to #55.

ReasoningGPQA Diamond (Epoch AI runs)Grok 4.20Fell from #52 to #53.

ReasoningGPQA Diamond (Epoch AI runs)Doubao Seed 2.1 Pro 260628Fell from #52 to #53.

ReasoningGPQA Diamond (Epoch AI runs)Gemini 3 FlashFell from #51 to #52.

ReasoningGPQA Diamond (Epoch AI runs)Doubao Seed 2.1 Turbo 260628Fell from #50 to #51.

ReasoningGPQA Diamond (Epoch AI runs)Claude Haiku 5.5Fell from #49 to #50.

ReasoningGPQA Diamond (Epoch AI runs)Muse SparkFell from #48 to #49.

ReasoningGPQA Diamond (Epoch AI runs)GLM-5.1Fell from #47 to #48.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 4.7Fell from #44 to #45.

ReasoningGPQA Diamond (Epoch AI runs)GLM 5.3 FlashFell from #44 to #45.

ReasoningGPQA Diamond (Epoch AI runs)Mistral Large 4 0 OSSFell from #44 to #45.

ReasoningGPQA Diamond (Epoch AI runs)GPT-6 LunaFell from #43 to #44.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 4.6Fell from #41 to #42.

ReasoningGPQA Diamond (Epoch AI runs)Claude Sonnet 5Fell from #41 to #42.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 5.5Fell from #40 to #41.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.5Fell from #39 to #40.

ReasoningGPQA Diamond (Epoch AI runs)Kimi K2.6Fell from #38 to #39.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.7-MaxFell from #35 to #36.

ReasoningGPQA Diamond (Epoch AI runs)MiniMax-M3Fell from #35 to #36.

ReasoningGPQA Diamond (Epoch AI runs)GLM-5.3Fell from #35 to #36.

ReasoningGPQA Diamond (Epoch AI runs)Claude Opus 4.8Fell from #33 to #34.

ReasoningGPQA Diamond (Epoch AI runs)DeepSeek V4 Flash VisionFell from #33 to #34.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.2Fell from #32 to #33.

ReasoningGPQA Diamond (Epoch AI runs)GPT-5.6 LunaFell from #31 to #32.

ReasoningGPQA Diamond (Epoch AI runs)DeepSeek V4 Pro 0813Fell from #30 to #31.

ReasoningGPQA Diamond (Epoch AI runs)GLM-5.2Fell from #29 to #30.

ReasoningGPQA Diamond (Epoch AI runs)Gemini 3 ProFell from #28 to #29.

ReasoningGPQA Diamond (Epoch AI runs)Qwen3.8 Max (0902)Fell from #27 to #28.

What changed on the AI leaderboards