Head to head on 23 boards: Anthropic places best on 12, OpenAI places best on 9 and MiniMax places best on 2. All 3 ranked on 13 of 27 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read |  MiniMax |  OpenAI |  Anthropic |
|---|
| Chat2 | | | | |
|---|
 MultiChallengeScoretodaytoday | Nov 9todaytoday | | #182.0%best of the pickedGPT-6.1 Sol | #1067.7%Claude Haiku 5.5 |
 Text ArenaArena ratingtodaytoday | Nov 9todaytoday | | #191,485GPT-5.6 Sol | #41,505best of the pickedClaude Opus 5.5 |
| Reasoning7 | | | | |
|---|
 Epoch ECIECItodaytoday | Nov 9todaytoday | #72147.6MiniMax-M3 | #1169.1best of the pickedGPT-6 Astra | #3168.4Claude Opus 5.5 |
 ARC-AGI-2Scoretodaytoday | Nov 9todaytoday | #644.9%MiniMax-M2.5 | #195.0%best of the pickedGPT-6 Astra | #393.3%Claude Opus 5.5 |
 LiveBenchGlobal averagetodaytoday | Nov 9todaytoday | #5967.3%MiniMax-M3 | #482.2%GPT-6 Astra | #183.4%best of the pickedClaude Fable 5.1 |
 AA IntelligenceIndextodaytoday | Nov 9todaytoday | #2229.1MiniMax-M3.1-Flash | #356.9GPT-6 Astra | #259.1best of the pickedClaude Opus 5.5 |
| GPQA DiamondAccuracytodaytoday | Nov 9todaytoday | #3490.9%MiniMax-M3 | #295.8%best of the pickedGPT-6 Astra | #395.6%Claude Sonnet 5.5 |
 MMLU-ProAccuracy · staletodaytoday | Nov 9todaytoday | #688.0%MiniMax M2.1 | #389.3%best of the pickedo1 | #489.1%Claude Opus 4.6 |
| HLEAccuracytodaytoday | Nov 9todaytoday | | #154.8%best of the pickedGPT-6 Astra | #246.5%Claude Fable 5.1 |
| Coding4 | | | | |
|---|
| WebDev ArenaArena ratingtodaytoday | Nov 9todaytoday | #341,582MiniMax-M3.1-Flash | #31,770GPT-6 Astra | #11,814best of the pickedClaude Opus 5.5 |
| SWE-Bench ProResolvedtodaytoday | Nov 9todaytoday | #1084.3%MiniMax M3P1 Flash | #490.2%GPT-6 Astra | #198.0%best of the pickedClaude Opus 5 |
 SWE-bench VerifiedResolved · staletodaytoday | Nov 9todaytoday | #275.8%MiniMax-M2.5 | #672.8%GPT-5.2 | #176.8%best of the pickedClaude Opus 4.5 |
 Aider PolyglotPass rate · staletodaytoday | Nov 9todaytoday | | #188.0%best of the pickedGPT-5 | #1072.0%Claude Opus 4 |
| Agents and tools3 | | | | |
|---|
 BFCLOverall accuracy · staletodaytoday | Nov 9todaytoday | | #763.0%o3 | #177.5%best of the pickedClaude Opus 4.5 |
| Search ArenaArena ratingtodaytoday | Nov 9todaytoday | | #11,255best of the pickedGPT-5.6 Sol | #51,229Claude Fable 5 |
| MCP AtlasPass ratetodaytoday | Nov 9todaytoday | | #1481.8%GPT-5.6 | #387.2%best of the pickedClaude Fable 5.1 |
| Vision2 | | | | |
|---|
| Vision ArenaArena ratingtodaytoday | Nov 9todaytoday | #611,231MiniMax-M3 | #81,293GPT-6.1 Sol | #11,309best of the pickedClaude Fable 5 |
| Document ArenaArena ratingtodaytoday | Nov 9todaytoday | #351,435MiniMax-M3 | #51,486GPT-5.6 Sol | #11,499best of the pickedClaude Fable 5 |
| Image2 | | | | |
|---|
| Text-to-ImageArena ratingtodaytoday | Nov 9todaytoday | | #11,429GPT Image 2.5 Sunburst | |
| Image EditArena ratingtodaytoday | Nov 9todaytoday | | #11,517GPT Image 2.5 Sunburst | |
| Video2 | | | | |
|---|
| Text-to-VideoArena ratingtodaytoday | Nov 9todaytoday | #111,457best of the pickedMiniMax H3 | #131,367Sora 2 Pro | |
| Image-to-VideoArena ratingtodaytoday | Nov 9todaytoday | #21,493MiniMax H3 | | |
| Speech2 | | | | |
|---|
| Speech ArenaArena ratingtodaytoday | Nov 9todaytoday | #271,175best of the pickedSpeech 2.8 Hd | #421,107TTS 1 Hd | |
 Open ASRAverage WERtodaytoday | Nov 9todaytoday | | #186.80 WERgpt-transcribe (openai) | |
| Speed1 | | | | |
|---|
| AA SpeedOutput speedtodaytoday | Nov 9todaytoday | #1717 tok/sMiniMax-M3.1-Flash | #1522 tok/sGPT-6.1 Sol | #931 tok/sbest of the pickedClaude Sonnet 5.5 |
| Price1 | | | | |
|---|
| AA PriceBlended pricetodaytoday | Nov 9todaytoday | | #6$2.00GPT-6.1 Terra | #1$0.20best of the pickedClaude Haiku 5.5 |
| Usage1 | | | | |
|---|
 OpenRouterWeekly tokenstodaytoday | Nov 9todaytoday | #75.0T tokMiniMax-M3.1-Flash | #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