T Thinky OpenAI Google Head to head on 25 boards: Google places best on 13 , OpenAI places best on 12 and Thinky places best on 0 . All 3 ranked on 11 of 28 boards.
Two at a time on this screen. Tap one to swap it in.
T Thinky OpenAI Google Board Read T Thinky OpenAI Google Chat2 Text Arena Arena rating 1d yesterday Nov 9 1d yesterday #75 1,443 Inkling #19 1,485 GPT-5.6 Sol #1 1,526 best of the picked Gemini 4 Carbon MultiChallenge Score 1d yesterday Nov 9 1d yesterday #1 82.0% best of the picked GPT-6.1 Sol #2 78.7% Gemini 4 Argon Reasoning7 AA Intelligence Index 1d yesterday Nov 9 1d yesterday #36 12.9 Inkling Small #3 56.9 GPT-6 Astra #1 60.0 best of the picked Gemini 4 Carbon GPQA Diamond Accuracy 1d yesterday Nov 9 1d yesterday #55 88.5% Inkling Small #2 95.8% GPT-6 Astra #1 96.4% best of the picked Gemini 4 Argon Epoch ECI ECI 1d yesterday Nov 9 1d yesterday #60 150.8 Inkling Small #1 169.1 best of the picked GPT-6 Astra #6 166.4 Gemini 4 Argon ARC-AGI-2 Score 1d yesterday Nov 9 1d yesterday #44 40.1% Inkling Small #1 95.0% best of the picked GPT-6 Astra #5 91.3% Gemini 4 Argon LiveBench Global average 1d yesterday Nov 9 1d yesterday #49 71.9% Inkling #4 82.2% best of the picked GPT-6 Astra #15 78.8% Gemini 3.7 Flash HLE Accuracy 1d yesterday Nov 9 1d yesterday #1 54.8% best of the picked GPT-6 Astra #3 46.4% Gemini 3.1 Pro Preview MMLU-Pro Accuracy · stale 1d yesterday Nov 9 1d yesterday #3 89.3% o1 #1 91.2% best of the picked Gemini 3.1 Pro Preview Coding4 WebDev Arena Arena rating 1d yesterday Nov 9 1d yesterday #79 1,415 Inkling #3 1,770 best of the picked GPT-6 Astra #4 1,767 Gemini 4 Carbon SWE-Bench Pro Resolved 1d yesterday Nov 9 1d yesterday #16 56.9% Inkling #4 90.2% GPT-6 Astra #3 92.2% best of the picked Gemini 4 Argon Aider Polyglot Pass rate · stale 1d yesterday Nov 9 1d yesterday #1 88.0% best of the picked GPT-5 #3 83.1% Gemini 2.5 Pro (Jun 2025) SWE-bench Verified Resolved · stale 1d yesterday Nov 9 1d yesterday #6 72.8% GPT-5.2 #2 75.8% best of the picked Gemini 3 Flash Agents and tools3 MCP Atlas Pass rate 1d yesterday Nov 9 1d yesterday #15 79.2% Inkling Small #14 81.8% GPT-5.6 #1 90.7% best of the picked Gemini 4 Argon Search Arena Arena rating 1d yesterday Nov 9 1d yesterday #1 1,255 best of the picked GPT-5.6 Sol #14 1,208 Gemini 3.1 Pro Preview BFCL Overall accuracy · stale 1d yesterday Nov 9 1d yesterday #7 63.0% o3 #3 72.5% best of the picked Gemini 3 Pro Vision2 Vision Arena Arena rating 1d yesterday Nov 9 1d yesterday #75 1,208 Inkling Small #8 1,293 GPT-6.1 Sol #6 1,294 best of the picked Gemini 3.7 Flash Document Arena Arena rating 1d yesterday Nov 9 1d yesterday #5 1,486 best of the picked GPT-5.6 Sol #16 1,469 Gemini 3.8 Flash Image2 Text-to-Image Arena rating 1d yesterday Nov 9 1d yesterday #1 1,429 best of the picked GPT Image 2.5 Sunburst #7 1,325 Gemini Nano Banana 2.1 Image Edit Arena rating 1d yesterday Nov 9 1d yesterday #1 1,517 best of the picked GPT Image 2.5 Sunburst #8 1,427 Gemini Nano Banana 2.1 Video2 Text-to-Video Arena rating 1d yesterday Nov 9 1d yesterday #13 1,367 Sora 2 Pro #1 1,541 best of the picked Gemini Omni 1.2 Flash Image-to-Video Arena rating 1d yesterday Nov 9 1d yesterday #1 1,502 Gemini Omni 1.2 Flash Speech2 Speech Arena Arena rating 1d yesterday Nov 9 1d yesterday #42 1,107 TTS 1 Hd #6 1,283 best of the picked Gemini 3.8 Flash TTS Open ASR Average WER 1d yesterday Nov 9 1d yesterday #18 6.80 WER best of the picked gpt-transcribe (openai) #58 13.20 WER gemma-4-E4B-it (google) Embeddings1 MTEB Mean task score 1d yesterday Nov 9 1d yesterday #5 68.4% gemini-embedding-001 (google) Speed1 AA Speed Output speed 1d yesterday Nov 9 1d yesterday #30 8 tok/s Inkling #15 22 tok/s GPT-6.1 Sol #7 35 tok/s best of the picked Gemini 4 Carbon Price1 AA Price Blended price 1d yesterday Nov 9 1d yesterday #6 $2.00 GPT-6.1 Terra #5 $1.50 best of the picked Gemini 3.8 Flash Usage1 OpenRouter Weekly tokens 1d yesterday Nov 9 1d yesterday #4 7.2T 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.