Head to head on 20 boards: Google places best on 16, Microsoft places best on 4 and MiniMax places best on 1 (a tie counts for each). All 3 ranked on 2 of 28 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read |  MiniMax |  Google |  Microsoft |
|---|
| Chat2 | | | | |
|---|
 Text ArenaArena rating1dyesterday | Nov 91dyesterday | | #11,526Gemini 4 Carbon | |
 MultiChallengeScore1dyesterday | Nov 91dyesterday | | #278.7%Gemini 4 Argon | |
| Reasoning7 | | | | |
|---|
 MMLU-ProAccuracy · stale1dyesterday | Nov 91dyesterday | #688.0%MiniMax M2.1 | #191.2%best of the pickedGemini 3.1 Pro Preview | #7576.0%Phi 4 Plus |
 AA IntelligenceIndex1dyesterday | Nov 91dyesterday | #2229.1MiniMax-M3.1-Flash | #160.0best of the pickedGemini 4 Carbon | |
 GPQA DiamondAccuracy1dyesterday | Nov 91dyesterday | #3490.9%MiniMax-M3 | #196.4%best of the pickedGemini 4 Argon | |
 ARC-AGI-2Score1dyesterday | Nov 91dyesterday | #644.9%MiniMax-M2.5 | #591.3%best of the pickedGemini 4 Argon | |
| Epoch ECIECI1dyesterday | Nov 91dyesterday | #72147.6MiniMax-M3 | #6166.4best of the pickedGemini 4 Argon | |
 LiveBenchGlobal average1dyesterday | Nov 91dyesterday | #5967.3%MiniMax-M3 | #1578.8%best of the pickedGemini 3.7 Flash | |
| HLEAccuracy1dyesterday | Nov 91dyesterday | | #346.4%Gemini 3.1 Pro Preview | |
| Coding4 | | | | |
|---|
 SWE-bench VerifiedResolved · stale1dyesterday | Nov 91dyesterday | #275.8%best of the pickedMiniMax-M2.5 | #275.8%best of the pickedGemini 3 Flash | |
| SWE-Bench ProResolved1dyesterday | Nov 91dyesterday | #1084.3%MiniMax M3P1 Flash | #392.2%best of the pickedGemini 4 Argon | |
| WebDev ArenaArena rating1dyesterday | Nov 91dyesterday | #341,582MiniMax-M3.1-Flash | #41,767best of the pickedGemini 4 Carbon | |
 Aider PolyglotPass rate · stale1dyesterday | Nov 91dyesterday | | #383.1%Gemini 2.5 Pro (Jun 2025) | |
| Agents and tools3 | | | | |
|---|
 BFCLOverall accuracy · stale1dyesterday | Nov 91dyesterday | | #372.5%best of the pickedGemini 3 Pro | #5028.8%Phi 4 |
| MCP AtlasPass rate1dyesterday | Nov 91dyesterday | | #190.7%Gemini 4 Argon | |
| Search ArenaArena rating1dyesterday | Nov 91dyesterday | | #141,208Gemini 3.1 Pro Preview | |
| Vision2 | | | | |
|---|
| Vision ArenaArena rating1dyesterday | Nov 91dyesterday | #611,231MiniMax-M3 | #61,294best of the pickedGemini 3.7 Flash | |
| Document ArenaArena rating1dyesterday | Nov 91dyesterday | #351,435MiniMax-M3 | #161,469best of the pickedGemini 3.8 Flash | |
| Image2 | | | | |
|---|
| Image EditArena rating1dyesterday | Nov 91dyesterday | | #81,427Gemini Nano Banana 2.1 | #41,467best of the pickedMAI Image 2.7 |
| Text-to-ImageArena rating1dyesterday | Nov 91dyesterday | | #71,325Gemini Nano Banana 2.1 | #61,330best of the pickedMAI Image 2.6 |
| Video2 | | | | |
|---|
| Text-to-VideoArena rating1dyesterday | Nov 91dyesterday | #111,457MiniMax H3 | #11,541best of the pickedGemini Omni 1.2 Flash | |
| Image-to-VideoArena rating1dyesterday | Nov 91dyesterday | #21,493MiniMax H3 | #11,502best of the pickedGemini Omni 1.2 Flash | |
| Speech2 | | | | |
|---|
| Speech ArenaArena rating1dyesterday | Nov 91dyesterday | #271,175Speech 2.8 Hd | #61,283best of the pickedGemini 3.8 Flash TTS | #311,145Azure Hd 2.5 |
 Open ASRAverage WER1dyesterday | Nov 91dyesterday | | #5813.20 WERgemma-4-E4B-it (google) | #35.55 WERbest of the pickedazure-speech-09-2026 (microsoft) |
| Embeddings1 | | | | |
|---|
| MTEBMean task score1dyesterday | Nov 91dyesterday | | #568.4%gemini-embedding-001 (google) | #174.3%best of the pickedharrier-oss-v1-27b (microsoft) |
| Speed1 | | | | |
|---|
| AA SpeedOutput speed1dyesterday | Nov 91dyesterday | #1717 tok/sMiniMax-M3.1-Flash | #735 tok/sbest of the pickedGemini 4 Carbon | |
| Price1 | | | | |
|---|
| AA PriceBlended price1dyesterday | Nov 91dyesterday | | #5$1.50Gemini 3.8 Flash | |
| Usage1 | | | | |
|---|
 OpenRouterWeekly tokens1dyesterday | Nov 91dyesterday | #75.0T tokMiniMax-M3.1-Flash | | |
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