AutoRLBench 40 Issue / 20 Solution - Solution: leaderboard

Solution-implementation split (20 tasks) of Thinking-Space AutoRLBench 40-issue / 20-solution edition measuring whether agents implement working fixes that pass held-out RL training checks; pass rate (%).

Metric: Repaired run passes its rerun, 20 tasks (%). Source: thinking-space.github.io. Saturation forecast: Around September 2028. 7 models tracked. Updated 19 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.1 SolMax40#15
2GLM-5.3Max35#73
3Qwen 3.8 MaxMax30#66
4Claude Fable 5.1Max25#20
5Kimi K3Max20#61
6Grok 4.7Max20#51
7DeepSeek V4 ProMax10#198

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-solution · How It Works · Data refreshed daily, snapshot 2026-11-20.