Head to head on 8 boards: DeepSeek places best on 5, Xiaomi places best on 2 and Microsoft places best on 1. All 3 ranked on 0 of 21 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read |  Xiaomi |  Microsoft |  DeepSeek |
|---|
| Chat2 | | | | |
|---|
 Text ArenaArena rating1dyesterday | Nov 91dyesterday | #261,479best of the pickedMiMo-V2.6-Pro | | #321,475DeepSeek V4.1 Flash |
 MultiChallengeScore1dyesterday | Nov 91dyesterday | | | #574.9%DeepSeek V4P1 Flash |
| Reasoning6 | | | | |
|---|
 AA IntelligenceIndex1dyesterday | Nov 91dyesterday | #2029.9MiMo-V2.6-Pro | | #1632.6best of the pickedDeepSeek V4.1 Flash |
 MMLU-ProAccuracy · stale1dyesterday | Nov 91dyesterday | | #7576.0%Phi 4 Plus | #3385.0%best of the pickedDeepSeek-V3.2 |
 LiveBenchGlobal average1dyesterday | Nov 91dyesterday | | | #881.1%DeepSeek V4.1 Flash |
 Epoch ECIECI1dyesterday | Nov 91dyesterday | | | #19159.3DeepSeek V4.1 Flash |
 ARC-AGI-2Score1dyesterday | Nov 91dyesterday | | | #1978.1%DeepSeek V4.1 Flash |
| GPQA DiamondAccuracy1dyesterday | Nov 91dyesterday | | | #2193.2%DeepSeek V4.1 Flash |
| Coding3 | | | | |
|---|
| WebDev ArenaArena rating1dyesterday | Nov 91dyesterday | #201,636MiMo-V2.6-Flash | | #141,665best of the pickedDeepSeek V4.1 Flash |
 Aider PolyglotPass rate · stale1dyesterday | Nov 91dyesterday | | | #874.2%DeepSeek-V3.2 |
 SWE-bench VerifiedResolved · stale1dyesterday | Nov 91dyesterday | | | #1170.0%DeepSeek-V3.2 |
| Agents and tools1 | | | | |
|---|
 BFCLOverall accuracy · stale1dyesterday | Nov 91dyesterday | | #5028.8%Phi 4 | #1256.7%best of the pickedDeepSeek-V3.2 |
| Vision1 | | | | |
|---|
| Vision ArenaArena rating1dyesterday | Nov 91dyesterday | #481,248MiMo-V2.6-Flash | | #341,263best of the pickedDeepSeek V4.1 Flash |
| Image2 | | | | |
|---|
| Image EditArena rating1dyesterday | Nov 91dyesterday | | #41,467MAI Image 2.7 | |
| Text-to-ImageArena rating1dyesterday | Nov 91dyesterday | | #61,330MAI Image 2.6 | |
| Speech2 | | | | |
|---|
| Speech ArenaArena rating1dyesterday | Nov 91dyesterday | #681,052MiMo V2.5 TTS | #311,145best of the pickedAzure Hd 2.5 | |
 Open ASRAverage WER1dyesterday | Nov 91dyesterday | | #35.55 WERazure-speech-09-2026 (microsoft) | |
| Embeddings1 | | | | |
|---|
| MTEBMean task score1dyesterday | Nov 91dyesterday | | #174.3%harrier-oss-v1-27b (microsoft) | |
| Speed1 | | | | |
|---|
| AA SpeedOutput speed1dyesterday | Nov 91dyesterday | #164 tok/sbest of the pickedMiMo-V2.6-Flash | | #1323 tok/sDeepSeek V4 Pro 0813 |
| Price1 | | | | |
|---|
| AA PriceBlended price1dyesterday | Nov 91dyesterday | | | #3$0.53DeepSeek V4.1 Flash |
| Usage1 | | | | |
|---|
 OpenRouterWeekly tokens1dyesterday | Nov 91dyesterday | | | #156.0T tokDeepSeek V4.1 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