AA Coding Agent Index v2.1 - SWE-Atlas-QnA-AA: leaderboard

Artificial Analysis Coding Agent Index v2.1 (November 2026) evaluates a model inside its named coding-agent harness. It averages FrontierCode-AA 2.0 (132 repository-editing tasks), Terminal-Bench 4.1 (66 terminal tasks with revised verifiers), and SWE-Atlas-QnA-AA (124 repository questions), each using three attempts per task and task-equal means. Audited reward-hacking attempts score zero; environment/verifier errors are excluded. Native model effort and harness remain separate; this edition differs from v2.0. This board reports SWE-Atlas-QnA-AA, higher is better.

Metric: Task Resolve Rate (%). Source: artificialanalysis.ai. Saturation forecast: Around 2029. 23 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Muse Wonder FullMax68.82#17
2Claude Fable 5.1Max, Default Fallback, AA Coding Agent Run: harness=Claude Code; native=Claude Fable 5.1 (Max, Default Fallback); fallback=source-published66.4#15
3Claude Opus 5.5Max, Default Fallback, AA Coding Agent Run: harness=Claude Code; native=Claude Opus 5.5 (Max, Default Fallback); fallback=source-published65.86#5
4Claude Sonnet 5.5Max, Default Fallback, AA Coding Agent Run: harness=Claude Code; native=Claude Sonnet 5.5 (Max, Default Fallback); fallback=source-published64.25#19
5Gemini 4 CarbonHigh63.71#2
6Claude Fable 5.2Medium, Default Fallback, AA Coding Agent Run: harness=Claude Code; native=Claude Fable 5.2 (Medium, Default Fallback); fallback=source-published63.71#1
7Grok 4.7xHigh62.9#47
8DeepSeek V4.1 Flash (1017)Max61.56#41
9Muse WonderMax61.56#28
10GPT-6.1 SolMax59.95#10
11GPT-6 AstraMax59.14#6
12Mistral Large 4High58.87#137
13GLM-5.3Max58.6#68
14Muse Spark 1.3Max58.6#43
15Step 5 Preview58.6#110

Interactive version: theaggregate.ai/benchmark?slug=aa-coding-agent-index-v2-1-swe-atlas-qna-aa · How It Works · Data refreshed daily, snapshot 2026-11-16.