AA Abr Ai Meta OpenAI DeepSeek Head to head on 25 boards: OpenAI places best on 18 , Meta places best on 6 , DeepSeek places best on 2 and Abr Ai places best on 0 (a tie counts for each). All 4 ranked on 0 of 26 boards.
Board Read AA Abr Ai Meta OpenAI DeepSeek 2 MultiChallenge Score 1d yesterday Nov 11 1d yesterday #3 75.5% Muse Spark #1 82.0% best of the picked GPT-6.1 Sol #5 74.9% DeepSeek V4P1 Flash Text Arena Arena rating 1d yesterday Nov 11 1d yesterday #3 1,511 best of the picked Muse Wonder #19 1,485 GPT-5.6 Sol #32 1,475 DeepSeek V4.1 Flash 7 ARC-AGI-2 Score 1d yesterday Nov 11 1d yesterday #41 57.5% Muse Spark Open #1 95.0% best of the picked GPT-6 Astra #21 78.1% DeepSeek V4.1 Flash Epoch ECI ECI 1d yesterday Nov 11 1d yesterday #15 162.0 Muse Wonder #2 169.2 best of the picked GPT-6 Astra #21 159.3 DeepSeek V4.1 Flash GPQA Diamond Accuracy 1d yesterday Nov 11 1d yesterday #49 89.8% Muse Spark #3 95.8% best of the picked GPT-6 Astra #23 93.2% DeepSeek V4.1 Flash MMLU-Pro Accuracy · stale 1d yesterday Nov 11 1d yesterday #47 82.8% Llama4 Behemoth #3 89.3% best of the picked o1 #33 85.0% DeepSeek-V3.2 AA Intelligence Index 1d yesterday Nov 11 1d yesterday #9 50.1 Muse Wonder Full #4 56.9 best of the picked GPT-6 Astra #17 32.6 DeepSeek V4.1 Flash LiveBench Global average 1d yesterday Nov 11 1d yesterday #6 81.6% Muse Spark 1.3 #4 82.2% best of the picked GPT-6 Astra #8 81.1% DeepSeek V4.1 Flash HLE Accuracy 1d yesterday Nov 11 1d yesterday #7 40.6% Muse Spark #1 54.8% best of the picked GPT-6 Astra 4 Aider Polyglot Pass rate · stale 1d yesterday Nov 11 1d yesterday #43 15.6% Llama 4 Maverick Instruct #1 88.0% best of the picked GPT-5 #8 74.2% DeepSeek-V3.2 WebDev Arena Arena rating 1d yesterday Nov 11 1d yesterday #8 1,723 Muse Wonder Full #5 1,764 best of the picked GPT-6 Astra #15 1,664 DeepSeek V4.1 Flash SWE-bench Verified Resolved · stale 1d yesterday Nov 11 1d yesterday #36 21.0% Llama 4 Maverick Instruct #6 72.8% best of the picked GPT-5.2 #11 70.0% DeepSeek-V3.2 SWE-Bench Pro Resolved 1d yesterday Nov 11 1d yesterday #4 90.2% best of the picked Muse Wonder 1.0 Max Effort #4 90.2% best of the picked GPT-6 Astra 3 BFCL Overall accuracy · stale 1d yesterday Nov 11 1d yesterday #36 37.3% Llama 4 Maverick 17b 128e #7 63.0% best of the picked o3 #12 56.7% DeepSeek-V3.2 MCP Atlas Pass rate 1d yesterday Nov 11 1d yesterday #2 88.1% best of the picked Muse Spark 1.1 #14 81.8% GPT-5.6 Search Arena Arena rating 1d yesterday Nov 11 1d yesterday #1 1,255 GPT-5.6 Sol 2 Vision Arena Arena rating 1d yesterday Nov 11 1d yesterday #6 1,294 best of the picked Muse Spark #10 1,293 GPT-6.1 Sol #35 1,263 DeepSeek V4.1 Flash Document Arena Arena rating 1d yesterday Nov 11 1d yesterday #9 1,480 Muse Spark 1.1 #5 1,486 best of the picked GPT-5.6 Sol 2 Text-to-Image Arena rating 1d yesterday Nov 11 1d yesterday #11 1,266 Muse Image #1 1,429 best of the picked GPT Image 2.5 Sunburst Image Edit Arena rating 1d yesterday Nov 11 1d yesterday #12 1,400 Muse Image #1 1,520 best of the picked GPT Image 2.5 Sunburst 1 Text-to-Video Arena rating 1d yesterday Nov 11 1d yesterday #10 1,457 best of the picked Muse Video #13 1,367 Sora 2 Pro 2 Open ASR Average WER 1d yesterday Nov 11 1d yesterday #55 10.90 WER niagara-84m-batch.en (abr-ai) #30 7.00 WER muse-voice-transcribe (meta) #19 6.80 WER best of the picked gpt-transcribe (openai) Speech Arena Arena rating 1d yesterday Nov 11 1d yesterday #99 846 Metavoice V1 #41 1,106 best of the picked TTS 1 Hd 1 AA Speed Output speed 1d yesterday Nov 11 1d yesterday #25 13 tok/s Muse Wonder #16 23 tok/s GPT-6 Astra #15 24 tok/s best of the picked DeepSeek V4 Pro 0813 1 AA Price Blended price 1d yesterday Nov 11 1d yesterday #1 $0.20 best of the picked Muse Ember #7 $2.00 GPT-6.1 Terra #4 $0.53 DeepSeek V4.1 Flash 1 OpenRouter Weekly tokens 1d yesterday Nov 11 1d yesterday #15 2.9T tok Muse Spark 1.3 Contributor #4 7.0T tok GPT-6 Luna #1 53.8T 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.
Modelsby GlyphMeta
OpenAI
DeepSeek