GPT-5.2 Muse Spark 1.1 Claude Fable 5.1 Head to head on 10 boards: Claude Fable 5.1 places best on 9 , Muse Spark 1.1 places best on 1 and GPT-5.2 places best on 0 . All 3 ranked on 7 of 19 boards.
Board Read GPT-5.2 Muse Spark 1.1 Claude Fable 5.1 Chat2 Text Arena Arena rating today today Nov 9 today today #29 1,476 #13 1,490 #6 1,504 best of the picked MultiChallenge Score today today Nov 9 today today #4 75.3% Reasoning7 LiveBench Global average today today Nov 9 today today #38 74.6% #35 75.3% #1 83.4% best of the picked Epoch ECI ECI today today Nov 9 today today #45 154.4 #42 154.9 #5 166.9 best of the picked HLE Accuracy today today Nov 9 today today #14 27.8% #2 46.5% best of the picked ARC-AGI-2 Score today today Nov 9 today today #41 52.9% #7 90.0% best of the picked AA Intelligence Index today today Nov 9 today today #9 50.0 MMLU-Pro Accuracy · stale today today Nov 9 today today #10 87.4% GPQA Diamond Accuracy today today Nov 9 today today #31 91.4% Coding3 WebDev Arena Arena rating today today Nov 9 today today #78 1,417 #44 1,542 #5 1,746 best of the picked SWE-Bench Pro Resolved today today Nov 9 today today #2 92.2% SWE-bench Verified Resolved · stale today today Nov 9 today today #6 72.8% Agents and tools3 MCP Atlas Pass rate today today Nov 9 today today #27 67.6% #2 88.1% best of the picked #3 87.2% Search Arena Arena rating today today Nov 9 today today #33 1,161 #7 1,227 best of the picked BFCL Overall accuracy · stale today today Nov 9 today today #14 55.9% Vision2 Document Arena Arena rating today today Nov 9 today today #37 1,425 #9 1,479 #2 1,499 best of the picked Vision Arena Arena rating today today Nov 9 today today #25 1,278 #24 1,279 #13 1,288 best of the picked Speed1 AA Speed Output speed today today Nov 9 today today #14 22 tok/s Price1 AA Price Blended price today today Nov 9 today today #17 $20.0
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.