Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.53.364ac010a008浙ICP备09076226号-7

Back to benchmarks

NL2RepoCoding

Official website

Results for 40 models collected from 21 public sources.

Ranking Sources

#ModelScore

1

Claude Opus 5Anthropic

72.3%

2

Claude Fable 5Anthropic

70.2%

3

Claude Opus 4.8Anthropic

69.7%

4

DeepSeek-V4.1-FlashDeepSeek · Technical report: 65.4; model card: 64.0 (source discrepancy).

65.4%

5

Qwen3.8-MaxAlibaba · 0902

64.9%

6

DeepSeek-V4-Pro-0813DeepSeek

61.5%

7

Claude Opus 4.7Anthropic

58.2%

8

Kimi K3Moonshot AI

58.0%

9

GLM-5.3Zhipu AI

58.0%

10

DeepSeek-V4-Flash-Vision-ExpDeepSeek

57.7%

40 models total

Benchmark details loading

Back to benchmarks

NL2RepoCoding

Official website

Results for 40 models collected from 21 public sources.

Ranking Sources

#ModelScore

1

Claude Opus 5Anthropic

72.3%

2

Claude Fable 5Anthropic

70.2%

3

Claude Opus 4.8Anthropic

69.7%

4

DeepSeek-V4.1-FlashDeepSeek · Technical report: 65.4; model card: 64.0 (source discrepancy).

65.4%

5

Qwen3.8-MaxAlibaba · 0902

64.9%

6

DeepSeek-V4-Pro-0813DeepSeek

61.5%

7

Claude Opus 4.7Anthropic

58.2%

8

Kimi K3Moonshot AI

58.0%

9

GLM-5.3Zhipu AI

58.0%

10

DeepSeek-V4-Flash-Vision-ExpDeepSeek

57.7%

40 models total