AutoRLBench 32 Issue / 18 Solution: leaderboard

AutoRLBench native 32-issue/18-solution task-set edition. Same published root-cause and repaired-workspace protocols, one run per model/task/level. Issue is an LLM judgment against hidden oracle; solution is the harness rerun metric threshold, with reward hacking failing. Overall counts passes over all50runs, not an average of two task-level rates. The source README announces32issue tasks and24solution-capable tasks, but exactly18 have scored solution runs; do not use24as the reported denominator. Exact task-ID sets are pinned and all rates reproduce the native table to its stated one decimal. Separate from the previously reviewed33/20task-set edition. This board reports Pass rate over 32 issue judgments and 18 solution runs (%). Higher is better.

Metric: Pass rate over 32 issue judgments and 18 solution runs (%). Source: thinking-space.github.io. Saturation forecast: Around December 2027. 10 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraMax46#6
2GPT-6.1 SolMax44#10
3Gemini 4 ArgonMax40#12
4GLM-5.3Max38#68
5Kimi K3.1 ProMax34#29
6Claude Fable 5.1Max32#15
7Qwen 3.8 MaxMax30#59
8Grok 4.7Max24#47
9DeepSeek V4 ProMax6#191
10Kimi K3Max4#56

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=autorlbench-32-issue-18-solution · How It Works · Data refreshed daily, snapshot 2026-11-16.