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

MMLU-ReduxReasoning

Official website

Results for 102 models collected from 15 public sources.

#ModelScore

1

Gemini 3 ProGoogle

95.9%

2

Claude Opus 4.5Anthropic

95.6%

3

Kimi-K2.6Moonshot AI

95.3%

4

Claude Opus 4.6Anthropic

95.2%

5

Qwen3.7-MaxAlibaba

95.0%

6

95.0%

7

Qwen3.5-397B-A17BAlibaba

94.9%

8

DeepSeek-V4-ProDeepSeek

94.8%

9

Qwen3.7-PlusAlibaba

94.5%

10

Qwen3.6-PlusAlibaba

94.5%

102 models total