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

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

MultiPL-ECoding

Results for 31 models collected from 3 public sources.

#ModelScore

Qwen3-235B-A22B-Instruct-2507Alibaba

87.9%

Qwen3-30B-A3B-Instruct-2507Alibaba

83.8%

Qwen3-4B-Instruct-2507Alibaba

76.8%

GPT-4.1 nano 2025-04-14OpenAI

76.3%

Qwen3-30B-A3BAlibaba · Initial April 2025 model · non-reasoning mode

74.6%

Qwen3-32B-BaseAlibaba

67.1%

Qwen3-4BAlibaba · Initial April 2025 model · non-reasoning mode

66.6%

Qwen3-30B-A3B-BaseAlibaba

66.5%

Qwen3-235B-A22B-BaseAlibaba

65.9%

DeepSeek-V3 BaseDeepSeek

62.3%

31 models total