Atlas

Benchmarks

← All benchmarks

NL2Repo - release-reported repository generation score

Code

Repository-level code generation from a natural-language specification. Exact task roster and aggregation are source-specific and unreported by the compared release tables; execution restrictions remain on config and score notes.

Top models (higher is better)

ModelScore
DeepSeek V4.1 Flash 101768.2
DeepSeek V4.1 Flash64.0
DeepSeek V4 Pro 081361.5
MiniMax M3.1 Flash61.2
GLM-5.358.0
Qwen3.8-Flash-Next48.1
Loading Atlas data…