Every AI leaderboard

28 leaderboards · 986 models ranked

Nvidia vs Anthropic vs OpenAI vs Google

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

  • Nvidia
  • Anthropic
  • OpenAI
  • Google

Head to head on 27 boards: OpenAI places best on 9, Anthropic places best on 8, Google places best on 8 and Nvidia places best on 2. All 4 ranked on 10 of 28 boards.

Two at a time on this screen. Tap one to swap it in.

BoardNvidiaAnthropicOpenAIGoogle
Chat2
Text ArenaArena ratingyesterday#41,505Claude Opus 5.5#191,485GPT-5.6 Sol#11,526best of the pickedGemini 4 Carbon
MultiChallengeScoreyesterday#1067.7%Claude Haiku 5.5#182.0%best of the pickedGPT-6.1 Sol#278.7%Gemini 4 Argon
Reasoning7
AA IntelligenceIndexyesterday#3513.6Nemotron 3.5 Super VL#259.1Claude Opus 5.5#356.9GPT-6 Astra#160.0best of the pickedGemini 4 Carbon
GPQA DiamondAccuracyyesterday#7585.4%Nemotron 3 Ultra#395.6%Claude Sonnet 5.5#295.8%GPT-6 Astra#196.4%best of the pickedGemini 4 Argon
Epoch ECIECIyesterday#76147.1Nemotron 3 Ultra#3168.4Claude Opus 5.5#1169.1best of the pickedGPT-6 Astra#6166.4Gemini 4 Argon
ARC-AGI-2Scoreyesterday#731.9%Nemotron 3.5 Super VL#393.3%Claude Opus 5.5#195.0%best of the pickedGPT-6 Astra#591.3%Gemini 4 Argon
LiveBenchGlobal averageyesterday#5867.4%Nemotron 3 Ultra 550B A55B#183.4%best of the pickedClaude Fable 5.1#482.2%GPT-6 Astra#1578.8%Gemini 3.7 Flash
MMLU-ProAccuracy · staleyesterday#7078.3%Nemotron 3 Nano 30b A3B#489.1%Claude Opus 4.6#389.3%o1#191.2%best of the pickedGemini 3.1 Pro Preview
HLEAccuracyyesterday#246.5%Claude Fable 5.1#154.8%best of the pickedGPT-6 Astra#346.4%Gemini 3.1 Pro Preview
Coding4
WebDev ArenaArena ratingyesterday#11,814best of the pickedClaude Opus 5.5#31,770GPT-6 Astra#41,767Gemini 4 Carbon
SWE-Bench ProResolvedyesterday#198.0%best of the pickedClaude Opus 5#490.2%GPT-6 Astra#392.2%Gemini 4 Argon
SWE-bench VerifiedResolved · staleyesterday#176.8%best of the pickedClaude Opus 4.5#672.8%GPT-5.2#275.8%Gemini 3 Flash
Aider PolyglotPass rate · staleyesterday#1072.0%Claude Opus 4#188.0%best of the pickedGPT-5#383.1%Gemini 2.5 Pro (Jun 2025)
Agents and tools3
BFCLOverall accuracy · staleyesterday#8010.0%Llama 3.1 Nemotron Ultra 253b V1#177.5%best of the pickedClaude Opus 4.5#763.0%o3#372.5%Gemini 3 Pro
MCP AtlasPass rateyesterday#2963.1%Nemotron 3 Ultra#387.2%Claude Fable 5.1#1481.8%GPT-5.6#190.7%best of the pickedGemini 4 Argon
Search ArenaArena ratingyesterday#51,229Claude Fable 5#11,255best of the pickedGPT-5.6 Sol#141,208Gemini 3.1 Pro Preview
Vision2
Vision ArenaArena ratingyesterday#731,211Nvidia Nemotron 3.5 Super VL 120b A12B#11,309best of the pickedClaude Fable 5#81,293GPT-6.1 Sol#61,294Gemini 3.7 Flash
Document ArenaArena ratingyesterday#11,499best of the pickedClaude Fable 5#51,486GPT-5.6 Sol#161,469Gemini 3.8 Flash
Image2
Text-to-ImageArena ratingyesterday#261,165Cosmos3 Super Text2image#11,429best of the pickedGPT Image 2.5 Sunburst#71,325Gemini Nano Banana 2.1
Image EditArena ratingyesterday#11,517best of the pickedGPT Image 2.5 Sunburst#81,427Gemini Nano Banana 2.1
Video2
Text-to-VideoArena ratingyesterday#131,367Sora 2 Pro#11,541best of the pickedGemini Omni 1.2 Flash
Image-to-VideoArena ratingyesterday#11,502Gemini Omni 1.2 Flash
Speech2
Speech ArenaArena ratingyesterday#591,064Magpie Multilingual 357m#421,107TTS 1 Hd#61,283best of the pickedGemini 3.8 Flash TTS
Open ASRAverage WERyesterday#96.13 WERbest of the pickedNVIDIA-Nemotron-3.5-Transcribe-30B-A4B (nvidia)#186.80 WERgpt-transcribe (openai)#5813.20 WERgemma-4-E4B-it (google)
Embeddings1
MTEBMean task scoreyesterday#369.5%best of the pickedllama-embed-nemotron-8b (nvidia)#568.4%gemini-embedding-001 (google)
Speed1
AA SpeedOutput speedyesterday#318 tok/sNemotron 3.5 Super VL#931 tok/sClaude Sonnet 5.5#1522 tok/sGPT-6.1 Sol#735 tok/sbest of the pickedGemini 4 Carbon
Price1
AA PriceBlended priceyesterday#1$0.20best of the pickedClaude Haiku 5.5#6$2.00GPT-6.1 Terra#5$1.50Gemini 3.8 Flash
Usage1
OpenRouterWeekly tokensyesterday#143.0T tokNemotron 3 Ultra 550B A55B#66.8T tokClaude Opus 5.5#47.2T tokbest of the pickedGPT-6 Luna

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.

More comparisons