NL2Repo-BenchBrowse 296

NL2Repo-Bench

Can the model complete substantial programming work under this benchmark's agent setup?

Version not specifiedExact reported variant
Coding9 ranked models9 reported values2 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

9
RankModelBest scoreBest reported setting
1Claude Opus 4.8Anthropic69.7%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
2DeepSeek V4.1 FlashDeepSeek65.4%Reported configurationDeepSeek report1 value · 1 reportSep 10, 2026 · source
3GPT-5.5OpenAI50.7%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
4GLM-5.2Z.ai48.9%max effortZ.ai report1 value · 1 reportJun 16, 2026 · source
5Qwen3.7-MaxQwen47.2%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
6GLM-5.1Z.ai42.7%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
7MiniMax M3MiniMax42.1%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
8DeepSeek V4 ProDeepSeek35.5%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source
9Gemini 3.1 ProGoogle33.4%Reported configurationZ.ai report1 value · 1 reportJun 16, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model complete substantial programming work under this benchmark's agent setup?

Software implementation, debugging, or repository work under the published evaluation protocol. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

DeepSeek's official V4.1-Flash release table; exact source benchmark label NL2Repo-Bench retained.

Method / source