Gemini 2.5 Pro (Jun 2025) GPT-6 Astra Qwen3.8 Max (0902) Head to head on 13 boards: GPT-6 Astra places best on 9 , Qwen3.8 Max (0902) places best on 4 and Gemini 2.5 Pro (Jun 2025) places best on 0 . All 3 ranked on 5 of 19 boards.
Board Read Gemini 2.5 Pro (Jun 2025) GPT-6 Astra Qwen3.8 Max (0902) Chat2 Text Arena Arena rating 1d yesterday Nov 9 1d yesterday #73 1,445 #31 1,475 #20 1,483 best of the picked MultiChallenge Score 1d yesterday Nov 9 1d yesterday #26 53.6% Reasoning7 Epoch ECI ECI 1d yesterday Nov 9 1d yesterday #88 144.8 #1 169.1 best of the picked #27 157.4 GPQA Diamond Accuracy 1d yesterday Nov 9 1d yesterday #76 85.3% #2 95.8% best of the picked #26 92.7% HLE Accuracy 1d yesterday Nov 9 1d yesterday #19 21.6% #1 54.8% best of the picked ARC-AGI-2 Score 1d yesterday Nov 9 1d yesterday #64 4.9% #1 95.0% best of the picked AA Intelligence Index 1d yesterday Nov 9 1d yesterday #3 56.9 best of the picked #15 33.7 LiveBench Global average 1d yesterday Nov 9 1d yesterday #4 82.2% best of the picked #16 78.5% MMLU-Pro Accuracy · stale 1d yesterday Nov 9 1d yesterday #29 86.0% Coding4 WebDev Arena Arena rating 1d yesterday Nov 9 1d yesterday #3 1,770 best of the picked #12 1,677 Aider Polyglot Pass rate · stale 1d yesterday Nov 9 1d yesterday #3 83.1% SWE-Bench Pro Resolved 1d yesterday Nov 9 1d yesterday #4 90.2% SWE-bench Verified Resolved · stale 1d yesterday Nov 9 1d yesterday #27 53.6% Agents and tools1 Search Arena Arena rating 1d yesterday Nov 9 1d yesterday #36 1,144 #3 1,245 best of the picked #6 1,228 Vision2 Vision Arena Arena rating 1d yesterday Nov 9 1d yesterday #50 1,248 #17 1,285 #2 1,300 best of the picked Document Arena Arena rating 1d yesterday Nov 9 1d yesterday #36 1,432 #11 1,477 best of the picked Speech1 Speech Arena Arena rating 1d yesterday Nov 9 1d yesterday #74 1,040 Speed1 AA Speed Output speed 1d yesterday Nov 9 1d yesterday #16 21 tok/s #2 60 tok/s best of the picked Price1 AA Price Blended price 1d yesterday Nov 9 1d yesterday #17 $20.0 #8 $3.00 best of the picked
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.