P P99lab Anthropic OpenAI Meta Head to head on 26 boards: Anthropic places best on 12 , OpenAI places best on 12 , Meta places best on 2 and P99lab places best on 1 (a tie counts for each). All 4 ranked on 0 of 26 boards.
Board Read P P99lab Anthropic OpenAI Meta 2 MultiChallenge Score 1d yesterday Oct 26 1d yesterday #8 67.7% Claude Haiku 5.5 #1 82.0% best of the picked GPT-6.1 Sol #3 75.5% Muse Spark Text Arena Arena rating 1d yesterday Oct 26 1d yesterday #2 1,509 best of the picked Claude Opus 5.5 #18 1,485 GPT-5.6 Sol #3 1,509 Muse Wonder 7 AA Intelligence Index 1d yesterday Oct 26 1d yesterday #1 57.6 best of the picked Claude Opus 5.5 #6 52.7 GPT-6 Astra #3 55.8 Muse Wonder Full HLE Accuracy 1d yesterday Oct 26 1d yesterday #2 46.5% Claude Fable 5.1 #1 54.8% best of the picked GPT-6 Astra #7 40.6% Muse Spark Epoch ECI ECI 1d yesterday Oct 26 1d yesterday #1 168.8 best of the picked Claude Opus 5.5 #2 168.8 GPT-6 Astra #12 161.8 Muse Wonder ARC-AGI-2 Score 1d yesterday Oct 26 1d yesterday #3 93.3% Claude Opus 5.5 #1 95.0% best of the picked GPT-6 Astra #38 57.5% Muse Spark Open LiveBench Global average 1d yesterday Oct 26 1d yesterday #1 83.4% best of the picked Claude Fable 5.1 #4 82.2% GPT-6 Astra #6 81.6% Muse Spark 1.3 GPQA Diamond Accuracy 1d yesterday Oct 26 1d yesterday #3 95.6% Claude Sonnet 5.5 #2 95.8% best of the picked GPT-6 Astra #43 89.8% Muse Spark MMLU-Pro Accuracy · stale 1d yesterday Oct 26 1d yesterday #4 89.1% Claude Opus 4.6 #3 89.3% best of the picked o1 #47 82.8% Llama4 Behemoth 4 WebDev Arena Arena rating 1d yesterday Oct 26 1d yesterday #1 1,807 best of the picked Claude Opus 5.5 #2 1,774 GPT-6 Astra #6 1,726 Muse Wonder Full SWE-Bench Pro Resolved 1d yesterday Oct 26 1d yesterday #1 98.0% best of the picked Claude Opus 5 #4 90.2% GPT-6 Astra #4 90.2% Muse Wonder 1.0 Max Effort SWE-bench Verified Resolved · stale 1d yesterday Oct 26 1d yesterday #1 76.8% best of the picked Claude Opus 4.5 #6 72.8% GPT-5.2 #36 21.0% Llama 4 Maverick Instruct Aider Polyglot Pass rate · stale 1d yesterday Oct 26 1d yesterday #10 72.0% Claude Opus 4 #1 88.0% best of the picked GPT-5 #43 15.6% Llama 4 Maverick Instruct 3 BFCL Overall accuracy · stale 1d yesterday Oct 26 1d yesterday #1 77.5% best of the picked Claude Opus 4.5 #7 63.0% o3 #36 37.3% Llama 4 Maverick 17b 128e MCP Atlas Pass rate 1d yesterday Oct 26 1d yesterday #2 87.2% Claude Fable 5.1 #11 81.8% GPT-5.6 #1 88.1% best of the picked Muse Spark 1.1 Search Arena Arena rating 1d yesterday Oct 26 1d yesterday #4 1,233 Claude Fable 5.1 #1 1,258 best of the picked GPT-5.6 Sol 2 Vision Arena Arena rating 1d yesterday Oct 26 1d yesterday #1 1,309 best of the picked Claude Fable 5 #7 1,294 GPT-6.1 Sol #6 1,294 Muse Spark Document Arena Arena rating 1d yesterday Oct 26 1d yesterday #1 1,499 best of the picked Claude Fable 5 #6 1,489 GPT-5.6 Sol #9 1,479 Muse Spark 1.1 2 Text-to-Image Arena rating 1d yesterday Oct 26 1d yesterday #1 1,425 best of the picked GPT Image 2.5 Sunburst #8 1,274 Muse Image Image Edit Arena rating 1d yesterday Oct 26 1d yesterday #1 1,514 best of the picked GPT Image 2.5 Sunburst #9 1,398 Muse Image 1 Text-to-Video Arena rating 1d yesterday Oct 26 1d yesterday #11 1,368 Sora 2 Pro #9 1,456 best of the picked Muse Video 2 Open ASR Average WER 1d yesterday Oct 26 1d yesterday #3 4.98 WER best of the picked audrey-0.7 (p99lab) #21 5.96 WER gpt-transcribe (openai) #32 6.30 WER muse-voice-transcribe (meta) Speech Arena Arena rating 1d yesterday Oct 26 1d yesterday #39 1,105 best of the picked TTS 1 Hd #95 846 Metavoice V1 1 AA Speed Output speed 1d yesterday Oct 26 1d yesterday #3 234 tok/s best of the picked Claude Haiku 5.5 #12 129 tok/s GPT-6 Luna #6 195 tok/s Muse Wonder 1 AA Price Blended price 1d yesterday Oct 26 1d yesterday #3 $0.20 best of the picked Claude Haiku 5.5 #3 $0.20 best of the picked GPT-6 Luna #17 $2.00 Muse Spark Open 1 OpenRouter Weekly tokens 1d yesterday Oct 26 1d yesterday #6 8.3T tok Claude Opus 5.5 #5 8.4T tok best of the picked GPT-6 Luna #15 2.8T tok Muse Spark 1.3 Contributor
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 GlyphAnthropic
OpenAI
Meta