MiniMax Microsoft DeepSeek ElevenLabs Head to head on 14 boards: DeepSeek places best on 10 , MiniMax places best on 2 , Microsoft places best on 1 and ElevenLabs places best on 1 . All 4 ranked on 0 of 25 boards.
Board Read MiniMax Microsoft DeepSeek ElevenLabs Chat2 MultiChallenge Score 1d yesterday Nov 9 1d yesterday #5 74.9% DeepSeek V4P1 Flash Text Arena Arena rating 1d yesterday Nov 9 1d yesterday #32 1,475 DeepSeek V4.1 Flash Reasoning6 MMLU-Pro Accuracy · stale 1d yesterday Nov 9 1d yesterday #6 88.0% best of the picked MiniMax M2.1 #75 76.0% Phi 4 Plus #33 85.0% DeepSeek-V3.2 LiveBench Global average 1d yesterday Nov 9 1d yesterday #59 67.3% MiniMax-M3 #8 81.1% best of the picked DeepSeek V4.1 Flash AA Intelligence Index 1d yesterday Nov 9 1d yesterday #22 29.1 MiniMax-M3.1-Flash #16 32.6 best of the picked DeepSeek V4.1 Flash Epoch ECI ECI 1d yesterday Nov 9 1d yesterday #72 147.6 MiniMax-M3 #19 159.3 best of the picked DeepSeek V4.1 Flash ARC-AGI-2 Score 1d yesterday Nov 9 1d yesterday #64 4.9% MiniMax-M2.5 #19 78.1% best of the picked DeepSeek V4.1 Flash GPQA Diamond Accuracy 1d yesterday Nov 9 1d yesterday #34 90.9% MiniMax-M3 #21 93.2% best of the picked DeepSeek V4.1 Flash Coding4 SWE-bench Verified Resolved · stale 1d yesterday Nov 9 1d yesterday #2 75.8% best of the picked MiniMax-M2.5 #11 70.0% DeepSeek-V3.2 WebDev Arena Arena rating 1d yesterday Nov 9 1d yesterday #34 1,582 MiniMax-M3.1-Flash #14 1,665 best of the picked DeepSeek V4.1 Flash Aider Polyglot Pass rate · stale 1d yesterday Nov 9 1d yesterday #8 74.2% DeepSeek-V3.2 SWE-Bench Pro Resolved 1d yesterday Nov 9 1d yesterday #10 84.3% MiniMax M3P1 Flash Agents and tools1 BFCL Overall accuracy · stale 1d yesterday Nov 9 1d yesterday #50 28.8% Phi 4 #12 56.7% best of the picked DeepSeek-V3.2 Vision2 Vision Arena Arena rating 1d yesterday Nov 9 1d yesterday #61 1,231 MiniMax-M3 #34 1,263 best of the picked DeepSeek V4.1 Flash Document Arena Arena rating 1d yesterday Nov 9 1d yesterday #35 1,435 MiniMax-M3 Image2 Image Edit Arena rating 1d yesterday Nov 9 1d yesterday #4 1,467 MAI Image 2.7 Text-to-Image Arena rating 1d yesterday Nov 9 1d yesterday #6 1,330 MAI Image 2.6 Video2 Image-to-Video Arena rating 1d yesterday Nov 9 1d yesterday #2 1,493 MiniMax H3 Text-to-Video Arena rating 1d yesterday Nov 9 1d yesterday #11 1,457 MiniMax H3 Speech2 Speech Arena Arena rating 1d yesterday Nov 9 1d yesterday #27 1,175 Speech 2.8 Hd #31 1,145 Azure Hd 2.5 #1 1,339 best of the picked Eleven V4 Open ASR Average WER 1d yesterday Nov 9 1d yesterday #3 5.55 WER best of the picked azure-speech-09-2026 (microsoft) #5 5.93 WER scribe v2 (elevenlabs) Embeddings1 MTEB Mean task score 1d yesterday Nov 9 1d yesterday #1 74.3% harrier-oss-v1-27b (microsoft) Speed1 AA Speed Output speed 1d yesterday Nov 9 1d yesterday #17 17 tok/s MiniMax-M3.1-Flash #13 23 tok/s best of the picked DeepSeek V4 Pro 0813 Price1 AA Price Blended price 1d yesterday Nov 9 1d yesterday #3 $0.53 DeepSeek V4.1 Flash Usage1 OpenRouter Weekly tokens 1d yesterday Nov 9 1d yesterday #7 5.0T tok MiniMax-M3.1-Flash #1 56.0T tok best of the picked DeepSeek 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.