Head to head on 24 boards: Anthropic places best on 12, OpenAI places best on 11 and Nvidia places best on 1. All 3 ranked on 11 of 27 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read |  Nvidia |  OpenAI |  Anthropic |
|---|
| Chat2 | | | | |
|---|
 MultiChallengeScore1dyesterday | Nov 91dyesterday | | #182.0%best of the pickedGPT-6.1 Sol | #1067.7%Claude Haiku 5.5 |
 Text ArenaArena rating1dyesterday | Nov 91dyesterday | | #191,485GPT-5.6 Sol | #41,505best of the pickedClaude Opus 5.5 |
| Reasoning7 | | | | |
|---|
 Epoch ECIECI1dyesterday | Nov 91dyesterday | #76147.1Nemotron 3 Ultra | #1169.1best of the pickedGPT-6 Astra | #3168.4Claude Opus 5.5 |
 ARC-AGI-2Score1dyesterday | Nov 91dyesterday | #731.9%Nemotron 3.5 Super VL | #195.0%best of the pickedGPT-6 Astra | #393.3%Claude Opus 5.5 |
 LiveBenchGlobal average1dyesterday | Nov 91dyesterday | #5867.4%Nemotron 3 Ultra 550B A55B | #482.2%GPT-6 Astra | #183.4%best of the pickedClaude Fable 5.1 |
 AA IntelligenceIndex1dyesterday | Nov 91dyesterday | #3513.6Nemotron 3.5 Super VL | #356.9GPT-6 Astra | #259.1best of the pickedClaude Opus 5.5 |
| GPQA DiamondAccuracy1dyesterday | Nov 91dyesterday | #7585.4%Nemotron 3 Ultra | #295.8%best of the pickedGPT-6 Astra | #395.6%Claude Sonnet 5.5 |
 MMLU-ProAccuracy · stale1dyesterday | Nov 91dyesterday | #7078.3%Nemotron 3 Nano 30b A3B | #389.3%best of the pickedo1 | #489.1%Claude Opus 4.6 |
| HLEAccuracy1dyesterday | Nov 91dyesterday | | #154.8%best of the pickedGPT-6 Astra | #246.5%Claude Fable 5.1 |
| Coding4 | | | | |
|---|
| WebDev ArenaArena rating1dyesterday | Nov 91dyesterday | | #31,770GPT-6 Astra | #11,814best of the pickedClaude Opus 5.5 |
| SWE-Bench ProResolved1dyesterday | Nov 91dyesterday | | #490.2%GPT-6 Astra | #198.0%best of the pickedClaude Opus 5 |
 SWE-bench VerifiedResolved · stale1dyesterday | Nov 91dyesterday | | #672.8%GPT-5.2 | #176.8%best of the pickedClaude Opus 4.5 |
 Aider PolyglotPass rate · stale1dyesterday | Nov 91dyesterday | | #188.0%best of the pickedGPT-5 | #1072.0%Claude Opus 4 |
| Agents and tools3 | | | | |
|---|
 BFCLOverall accuracy · stale1dyesterday | Nov 91dyesterday | #8010.0%Llama 3.1 Nemotron Ultra 253b V1 | #763.0%o3 | #177.5%best of the pickedClaude Opus 4.5 |
| MCP AtlasPass rate1dyesterday | Nov 91dyesterday | #2963.1%Nemotron 3 Ultra | #1481.8%GPT-5.6 | #387.2%best of the pickedClaude Fable 5.1 |
| Search ArenaArena rating1dyesterday | Nov 91dyesterday | | #11,255best of the pickedGPT-5.6 Sol | #51,229Claude Fable 5 |
| Vision2 | | | | |
|---|
| Vision ArenaArena rating1dyesterday | Nov 91dyesterday | #731,211Nvidia Nemotron 3.5 Super VL 120b A12B | #81,293GPT-6.1 Sol | #11,309best of the pickedClaude Fable 5 |
| Document ArenaArena rating1dyesterday | Nov 91dyesterday | | #51,486GPT-5.6 Sol | #11,499best of the pickedClaude Fable 5 |
| Image2 | | | | |
|---|
| Text-to-ImageArena rating1dyesterday | Nov 91dyesterday | #261,165Cosmos3 Super Text2image | #11,429best of the pickedGPT Image 2.5 Sunburst | |
| Image EditArena rating1dyesterday | Nov 91dyesterday | | #11,517GPT Image 2.5 Sunburst | |
| Video1 | | | | |
|---|
| Text-to-VideoArena rating1dyesterday | Nov 91dyesterday | | #131,367Sora 2 Pro | |
| Speech2 | | | | |
|---|
 Open ASRAverage WER1dyesterday | Nov 91dyesterday | #96.13 WERbest of the pickedNVIDIA-Nemotron-3.5-Transcribe-30B-A4B (nvidia) | #186.80 WERgpt-transcribe (openai) | |
| Speech ArenaArena rating1dyesterday | Nov 91dyesterday | #591,064Magpie Multilingual 357m | #421,107best of the pickedTTS 1 Hd | |
| Embeddings1 | | | | |
|---|
| MTEBMean task score1dyesterday | Nov 91dyesterday | #369.5%llama-embed-nemotron-8b (nvidia) | | |
| Speed1 | | | | |
|---|
| AA SpeedOutput speed1dyesterday | Nov 91dyesterday | #318 tok/sNemotron 3.5 Super VL | #1522 tok/sGPT-6.1 Sol | #931 tok/sbest of the pickedClaude Sonnet 5.5 |
| Price1 | | | | |
|---|
| AA PriceBlended price1dyesterday | Nov 91dyesterday | | #6$2.00GPT-6.1 Terra | #1$0.20best of the pickedClaude Haiku 5.5 |
| Usage1 | | | | |
|---|
 OpenRouterWeekly tokens1dyesterday | Nov 91dyesterday | #143.0T tokNemotron 3 Ultra 550B A55B | #47.2T tokbest of the pickedGPT-6 Luna | #66.8T tokClaude Opus 5.5 |
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.
Modelsby Glyph