Head to head on 21 boards: Google places best on 17, DeepSeek places best on 3 and Tencent places best on 1. All 3 ranked on 6 of 28 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read | Tencent | Google | DeepSeek |
|---|
| Chat2 | | | | |
|---|
Text ArenaArena rating1dyesterday | Nov 91dyesterday | #621,454Hy3 | #11,526best of the pickedGemini 4 Carbon | #321,475DeepSeek V4.1 Flash |
MultiChallengeScore1dyesterday | Nov 91dyesterday | | #278.7%best of the pickedGemini 4 Argon | #574.9%DeepSeek V4P1 Flash |
| Reasoning7 | | | | |
|---|
AA IntelligenceIndex1dyesterday | Nov 91dyesterday | #1434.6Tencent Hy4 | #160.0best of the pickedGemini 4 Carbon | #1632.6DeepSeek V4.1 Flash |
MMLU-ProAccuracy · stale1dyesterday | Nov 91dyesterday | #1587.2%Hunyuan T1 | #191.2%best of the pickedGemini 3.1 Pro Preview | #3385.0%DeepSeek-V3.2 |
GPQA DiamondAccuracy1dyesterday | Nov 91dyesterday | | #196.4%best of the pickedGemini 4 Argon | #2193.2%DeepSeek V4.1 Flash |
ARC-AGI-2Score1dyesterday | Nov 91dyesterday | | #591.3%best of the pickedGemini 4 Argon | #1978.1%DeepSeek V4.1 Flash |
Epoch ECIECI1dyesterday | Nov 91dyesterday | | #6166.4best of the pickedGemini 4 Argon | #19159.3DeepSeek V4.1 Flash |
LiveBenchGlobal average1dyesterday | Nov 91dyesterday | | #1578.8%Gemini 3.7 Flash | #881.1%best of the pickedDeepSeek V4.1 Flash |
HLEAccuracy1dyesterday | Nov 91dyesterday | | #346.4%Gemini 3.1 Pro Preview | |
| Coding4 | | | | |
|---|
WebDev ArenaArena rating1dyesterday | Nov 91dyesterday | #211,631Hy4 preview | #41,767best of the pickedGemini 4 Carbon | #141,665DeepSeek V4.1 Flash |
SWE-bench VerifiedResolved · stale1dyesterday | Nov 91dyesterday | | #275.8%best of the pickedGemini 3 Flash | #1170.0%DeepSeek-V3.2 |
Aider PolyglotPass rate · stale1dyesterday | Nov 91dyesterday | | #383.1%best of the pickedGemini 2.5 Pro (Jun 2025) | #874.2%DeepSeek-V3.2 |
SWE-Bench ProResolved1dyesterday | Nov 91dyesterday | | #392.2%Gemini 4 Argon | |
| Agents and tools3 | | | | |
|---|
BFCLOverall accuracy · stale1dyesterday | Nov 91dyesterday | | #372.5%best of the pickedGemini 3 Pro | #1256.7%DeepSeek-V3.2 |
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 | | #61,294best of the pickedGemini 3.7 Flash | #341,263DeepSeek V4.1 Flash |
Document ArenaArena rating1dyesterday | Nov 91dyesterday | | #161,469Gemini 3.8 Flash | |
| Image2 | | | | |
|---|
Text-to-ImageArena rating1dyesterday | Nov 91dyesterday | #301,151Hunyuanimage 3.0 | #71,325best of the pickedGemini Nano Banana 2.1 | |
Image EditArena rating1dyesterday | Nov 91dyesterday | #281,302Hunyuanimage 3.0 | #81,427best of the pickedGemini Nano Banana 2.1 | |
| Video2 | | | | |
|---|
Text-to-VideoArena rating1dyesterday | Nov 91dyesterday | #361,168Hunyuanvideo 1.5 | #11,541best of the pickedGemini Omni 1.2 Flash | |
Image-to-VideoArena rating1dyesterday | Nov 91dyesterday | #371,199Hunyuanvideo 1.5 | #11,502best of the pickedGemini Omni 1.2 Flash | |
| Speech2 | | | | |
|---|
Speech ArenaArena rating1dyesterday | Nov 91dyesterday | | #61,283Gemini 3.8 Flash TTS | |
Open ASRAverage WER1dyesterday | Nov 91dyesterday | | #5813.20 WERgemma-4-E4B-it (google) | |
| Embeddings1 | | | | |
|---|
MTEBMean task score1dyesterday | Nov 91dyesterday | #272.3%best of the pickedKaLM-Embedding-Gemma3-12B-2511 (tencent) | #568.4%gemini-embedding-001 (google) | |
| Speed1 | | | | |
|---|
AA SpeedOutput speed1dyesterday | Nov 91dyesterday | #2314 tok/sTencent Hy4 | #735 tok/sbest of the pickedGemini 4 Carbon | #1323 tok/sDeepSeek V4 Pro 0813 |
| Price1 | | | | |
|---|
AA PriceBlended price1dyesterday | Nov 91dyesterday | #4$1.25Tencent Hy4 | #5$1.50Gemini 3.8 Flash | #3$0.53best of the pickedDeepSeek V4.1 Flash |
| Usage1 | | | | |
|---|
OpenRouterWeekly tokens1dyesterday | Nov 91dyesterday | #312.8T tokHy4 preview | | #156.0T tokbest of the pickedDeepSeek 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.