P P99lab OpenAI Google Microsoft Head to head on 26 boards: OpenAI places best on 13 , Google places best on 11 , P99lab places best on 1 and Microsoft places best on 1 . All 4 ranked on 1 of 28 boards.
Board Read P P99lab OpenAI Google Microsoft 2 Text Arena Arena rating 1d yesterday Oct 26 1d yesterday #18 1,485 GPT-5.6 Sol #1 1,517 best of the picked Gemini 4 Argon MultiChallenge Score 1d yesterday Oct 26 1d yesterday #1 82.0% best of the picked GPT-6.1 Sol #2 78.7% Gemini 4 Argon 7 MMLU-Pro Accuracy · stale 1d yesterday Oct 26 1d yesterday #3 89.3% o1 #1 91.2% best of the picked Gemini 3.1 Pro Preview #75 76.0% Phi 4 Plus HLE Accuracy 1d yesterday Oct 26 1d yesterday #1 54.8% best of the picked GPT-6 Astra #3 46.4% Gemini 3.1 Pro Preview GPQA Diamond Accuracy 1d yesterday Oct 26 1d yesterday #2 95.8% GPT-6 Astra #1 96.4% best of the picked Gemini 4 Argon ARC-AGI-2 Score 1d yesterday Oct 26 1d yesterday #1 95.0% best of the picked GPT-6 Astra #5 91.3% Gemini 4 Argon Epoch ECI ECI 1d yesterday Oct 26 1d yesterday #2 168.8 best of the picked GPT-6 Astra #5 166.4 Gemini 4 Argon LiveBench Global average 1d yesterday Oct 26 1d yesterday #4 82.2% best of the picked GPT-6 Astra #15 78.8% Gemini 3.7 Flash AA Intelligence Index 1d yesterday Oct 26 1d yesterday #6 52.7 best of the picked GPT-6 Astra #7 52.6 Gemini 4 Argon 4 Aider Polyglot Pass rate · stale 1d yesterday Oct 26 1d yesterday #1 88.0% best of the picked GPT-5 #3 83.1% Gemini 2.5 Pro (Jun 2025) WebDev Arena Arena rating 1d yesterday Oct 26 1d yesterday #2 1,774 best of the picked GPT-6 Astra #10 1,674 Gemini 4 Argon SWE-bench Verified Resolved · stale 1d yesterday Oct 26 1d yesterday #6 72.8% GPT-5.2 #2 75.8% best of the picked Gemini 3 Flash SWE-Bench Pro Resolved 1d yesterday Oct 26 1d yesterday #4 90.2% GPT-6 Astra #3 92.2% best of the picked Gemini 4 Argon 3 BFCL Overall accuracy · stale 1d yesterday Oct 26 1d yesterday #7 63.0% o3 #3 72.5% best of the picked Gemini 3 Pro #50 28.8% Phi 4 Search Arena Arena rating 1d yesterday Oct 26 1d yesterday #1 1,258 best of the picked GPT-5.6 Sol #14 1,207 Gemini 3.1 Pro Grounding MCP Atlas Pass rate 1d yesterday Oct 26 1d yesterday #11 81.8% GPT-5.6 #6 83.6% best of the picked Gemini 3.5 Flash 2 Vision Arena Arena rating 1d yesterday Oct 26 1d yesterday #7 1,294 GPT-6.1 Sol #5 1,295 best of the picked Gemini 3.7 Flash Document Arena Arena rating 1d yesterday Oct 26 1d yesterday #6 1,489 best of the picked GPT-5.6 Sol #21 1,461 Gemini 3.5 Flash 2 Text-to-Image Arena rating 1d yesterday Oct 26 1d yesterday #1 1,425 best of the picked GPT Image 2.5 Sunburst #6 1,328 Gemini Nano Banana 2.1 #5 1,332 MAI Image 2.6 Image Edit Arena rating 1d yesterday Oct 26 1d yesterday #1 1,514 best of the picked GPT Image 2.5 Sunburst #5 1,426 Gemini Nano Banana 2.1 #6 1,425 MAI Image 2.6 2 Text-to-Video Arena rating 1d yesterday Oct 26 1d yesterday #11 1,368 Sora 2 Pro #1 1,516 best of the picked Gemini Omni 1.1 Flash Image-to-Video Arena rating 1d yesterday Oct 26 1d yesterday #2 1,488 Gemini Omni 1.1 Flash 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) #56 11.86 WER gemma-4-E4B-it (google) #4 5.02 WER azure-speech-07-2026 (microsoft) Speech Arena Arena rating 1d yesterday Oct 26 1d yesterday #39 1,105 TTS 1 Hd #5 1,280 best of the picked Gemini 3.8 Flash TTS #29 1,143 Azure Hd 2.5 1 MTEB Mean task score 1d yesterday Oct 26 1d yesterday #5 68.4% gemini-embedding-001 (google) #1 74.3% best of the picked harrier-oss-v1-27b (microsoft) 1 AA Speed Output speed 1d yesterday Oct 26 1d yesterday #12 129 tok/s GPT-6 Luna #11 132 tok/s best of the picked Gemini 3.8 Flash 1 AA Price Blended price 1d yesterday Oct 26 1d yesterday #3 $0.20 best of the picked GPT-6 Luna #15 $1.50 Gemini 3.8 Flash 1 OpenRouter Weekly tokens 1d yesterday Oct 26 1d yesterday #5 8.4T tok GPT-6 Luna
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 GlyphOpenAI
Google
Microsoft