SelfBench - getsentry/sentry: leaderboard

Coding agents implement changes rebuilt from the merged pull requests of the open-source repository getsentry/sentry: the pull request becomes the instruction and hidden tests written for it decide success. Each row is one model in one harness (Claude Code, Codex or pi) at one reasoning level. Task success rate, higher is better. Source: selfbench.dev.

Metric: Task success (%) on 78 tasks rebuilt from the repository's merged pull requests (hidden tests). Source: selfbench.dev. Saturation forecast: Around February 2027. 11 models tracked. Updated 13 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 5.5High82.05#7
2Claude Sonnet 5.5High82.05#21
3GPT-6.1 SolHigh80.77#12
4DeepSeek V4.1 Flash (1017)High79.49#44
5GPT-6 AstraMax78.21#8
6Kimi K3High76.92#59
7GLM-5.3High73.08#73
8Mistral Large 4 PreviewHigh69.23#206
9Claude Haiku 5.5High67.95#76
10DeepSeek V4.1 FlashHigh57.69#69
11GPT-6 LunaHigh51.28#105

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=selfbench-getsentry-sentry · How It Works · Data refreshed daily, snapshot 2026-11-17.