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

GPQAReasoning

Results for 29 models collected from 2 public sources.

#ModelScore

1

Gemini 3.1 ProGoogle

94.1%

2

91.0%

3

DeepSeek-V4-ProDeepSeek

90.1%

4

Claude Opus 4.6Anthropic

89.6%

5

Qwen3-32B-BaseAlibaba

49.5%

6

Qwen2.5-32BAlibaba

48.0%

7

Qwen3-235B-A22B-BaseAlibaba

47.5%

8

Qwen2.5-72BAlibaba

45.9%

9

Qwen3-8B-BaseAlibaba

44.4%

10

Qwen3-30B-A3B-BaseAlibaba

43.9%

29 models total