AutoRLBench 40 Issue / 20 Solution: leaderboard

Thinking-Space AutoRLBench 40-issue / 20-solution edition evaluating autonomous RL research agents end-to-end across 60 tasks (40 issue diagnosis and 20 solution implementation tasks) in sandboxed repositories; overall pass rate (%).

Metric: Pass rate over 40 issue judgments and 20 solution runs (%). Source: thinking-space.github.io. Saturation forecast: Around 2029. 6 models tracked. Updated 19 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.1 SolMax31.7#15
2GLM-5.3Max25#73
3Claude Fable 5.1Max18.3#20
4Qwen 3.8 MaxMax18.3#66
5Grok 4.7Max16.7#51
6Kimi K3Max6.7#61

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=autorlbench-40-issue-20-solution · How It Works · Data refreshed daily, snapshot 2026-11-20.