Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

MBPPCoding

Results for 25 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22B-BaseAlibaba

81.4%

2

Qwen3-32B-BaseAlibaba

78.2%

3

Qwen2.5-72BAlibaba

76.0%

4

Llama 4 Maverick BaseMeta

75.4%

5

Qwen2.5-Plus-BaseAlibaba

74.6%

6

Qwen3-30B-A3B-BaseAlibaba

74.4%

7

DeepSeek-V3 BaseDeepSeek

74.2%

8

Qwen2.5-32BAlibaba

73.6%

9

Qwen3-14B-BaseAlibaba

73.4%

10

Qwen3-8B-BaseAlibaba

69.8%

25 models total