R Reflection Meta OpenAI DeepSeek Head to head on 25 boards: OpenAI places best on 19 , Meta places best on 5 , Reflection places best on 1 and DeepSeek places best on 1 (a tie counts for each). All 4 ranked on 2 of 26 boards.
Board Read R Reflection Meta OpenAI DeepSeek Chat2 MultiChallenge Score today today Oct 21 today today #2 75.5% Muse Spark #1 82.0% best of the picked GPT-6.1 Sol #26 46.1% DeepSeek V3P1 Text Arena Arena rating today today Oct 21 today today #8 1,494 best of the picked Muse Spark 1.3 #17 1,485 GPT-5.6 Sol #34 1,475 DeepSeek V4.1 Flash Reasoning7 ARC-AGI-2 Score today today Oct 21 today today #46 23.5% Beam 1.0 #80 0.0% Llama 4 Maverick Instruct #1 95.0% best of the picked GPT-6 Astra #21 72.9% DeepSeek V4.1 Flash GPQA Diamond Accuracy today today Oct 21 today today #43 89.8% Muse Spark #2 95.8% best of the picked GPT-6 Astra #25 91.7% DeepSeek V4 Pro 0813 Epoch ECI ECI today today Oct 21 today today #12 161.8 Muse Wonder #2 168.8 best of the picked GPT-6 Astra #32 155.9 DeepSeek V4.1 Flash MMLU-Pro Accuracy · stale today today Oct 21 today today #47 82.8% Llama4 Behemoth #3 89.3% best of the picked o1 #33 85.0% DeepSeek-V3.2 LiveBench Global average today today Oct 21 today today #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 today today Oct 21 today today #7 40.6% Muse Spark #1 54.8% best of the picked GPT-6 Astra AA Intelligence Index today today Oct 21 today today #2 56.0 best of the picked Muse Wonder Full #4 53.0 GPT-6 Astra Coding4 Aider Polyglot Pass rate · stale today today Oct 21 today today #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 today today Oct 21 today today #10 1,656 Muse Spark 1.3 #2 1,788 best of the picked GPT-6 Astra #19 1,619 DeepSeek V4.1 Flash SWE-bench Verified Resolved · stale today today Oct 21 today today #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 today today Oct 21 today today #4 90.2% best of the picked Muse Wonder 1.0 Max Effort #4 90.2% best of the picked GPT-6 Astra Agents and tools3 BFCL Overall accuracy · stale today today Oct 21 today today #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 today today Oct 21 today today #1 88.1% best of the picked Muse Spark 1.1 #11 81.8% GPT-5.6 Search Arena Arena rating today today Oct 21 today today #1 1,257 GPT-5.6 Sol Vision2 Vision Arena Arena rating today today Oct 21 today today #7 1,294 Muse Spark #6 1,294 best of the picked GPT-6.1 Sol #39 1,260 DeepSeek V4.1 Flash Document Arena Arena rating today today Oct 21 today today #12 1,471 Muse Spark 1.3 #6 1,486 best of the picked GPT-5.5 Image2 Text-to-Image Arena rating today today Oct 21 today today #8 1,274 Muse Image #1 1,425 best of the picked GPT Image 2.5 Sunburst Image Edit Arena rating today today Oct 21 today today #7 1,403 Muse Image #1 1,524 best of the picked GPT Image 2.5 Sunburst Video1 Text-to-Video Arena rating today today Oct 21 today today #9 1,456 best of the picked Muse Video #11 1,368 Sora 2 Pro Speech2 Open ASR Average WER today today Oct 21 today today #35 6.48 WER muse-voice-transcribe (meta) #30 6.38 WER best of the picked gpt-transcribe (openai) Speech Arena Arena rating today today Oct 21 today today #95 847 Metavoice V1 #39 1,103 best of the picked TTS 1 Hd Speed1 AA Speed Output speed today today Oct 21 today today #6 345 tok/s best of the picked Beam 1.0 #7 281 tok/s Muse Spark 1.3 #9 266 tok/s GPT OSS 20b #16 209 tok/s DeepSeek V4.1 Flash Price1 AA Price Blended price today today Oct 21 today today #15 $2.00 Muse Spark 1.3 #3 $0.20 best of the picked GPT-6 Luna #8 $0.53 DeepSeek V4.1 Flash Usage1 OpenRouter Weekly tokens today today Oct 21 today today #12 3.3T tok Muse Spark 1.3 Contributor #6 6.2T tok GPT-6 Luna #1 27.3T 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.