NL2Repo-BenchBrowse 284 families
NL2Repo-Bench
Can the model complete substantial programming work under this benchmark's agent setup?
Version / measure
- Domain
- Coding
- Ranked models
- 9
- Reported values
- 9
- Reports
- 2 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | Claude Opus 4.8Anthropic | reportedcost n/a1 value · Jun 16 · source | 69.7% |
| 2 | DeepSeek V4.1 FlashDeepSeekOW | reportedcost n/a1 value · Sep 10 · source | 65.4% |
| 3 | GPT-5.5OpenAI | reportedcost n/a1 value · Jun 16 · source | 50.7% |
| 4 | GLM-5.2Z.aiOW | maxcost n/a1 value · Jun 16 · source | 48.9% |
| 5 | Qwen3.7-MaxQwen | reportedcost n/a1 value · Jun 16 · source | 47.2% |
| 6 | GLM-5.1Z.aiOW | reportedcost n/a1 value · Jun 16 · source | 42.7% |
| 7 | MiniMax M3MiniMaxOW | reportedcost n/a1 value · Jun 16 · source | 42.1% |
| 8 | DeepSeek V4 ProDeepSeekOW | reportedcost n/a1 value · Jun 16 · source | 35.5% |
| 9 | Gemini 3.1 ProGoogle | reportedcost n/a1 value · Jun 16 · source | 33.4% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
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 ↗