SWE-Atlas-QnA-AA benchmark: Muse Wonder Full tops revised repo Q&A grading at 68.8%
ArtificialAnlys · x · 2026-10-23
Artificial Analysis details the revised SWE-Atlas-QnA-AA benchmark in Coding Agent Index v2.0: same 124 Scale AI repo Q&A tasks, 127 of 1,306 rubric criteria reworded, and GPT-6 Luna (xhigh) as judge with five votes per criterion.
Muse Code + Muse Wonder Full (max) leads at 68.8%, followed by Claude Fable 5.1 (66.4%), Claude Opus 5.5 (65.9%) and Claude Sonnet 5.5 (64.2%). Across 21 overlapping configs the mean fell 1.7 points, with 14 moving down.
More from coding & agent
- NVIDIA unveils OpenShell Reference Architecture to set boundaries for enterprise AI agents — NicoVerderosa · 2026-10-23
- Most 'unauthorized' AI agents in US bank accounts were let in by customers themselves, per Axios — nptacek · 2026-10-23
- Personal AI agents become a capital-intensive race as cloud execution environments reshape cost structures — sujingshen · 2026-10-23
- LLMs make code so cheap that recursive rewrites could make verified software tractable — jd_pressman · 2026-10-23
- Hugging Face hands OpenEnv RL environments project to Linux Foundation for neutral governance — lmoroney · 2026-10-23
- Theo writes the definitive explainer on what an AI coding "harness" actually is — pvncher · 2026-10-23