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

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

MultiChallengeReasoning

Official website

Results for 22 models collected from 4 public sources.

#ModelScore

1

DeepSeek-V4-ProDeepSeek

64.1%

2

Qwen3.5-397B-A17BAlibaba

63.9%

3

Nemotron-3-UltraNVIDIA

63.8%

4

DeepSeek-V4-FlashDeepSeek

63.5%

5

Kimi-K2.6Moonshot AI

63.1%

6

GLM-5.1Zhipu AI

63.0%

7

Qwen3.5-122B-A10BAlibaba

61.5%

8

Qwen3.5-27BAlibaba

60.8%

9

Qwen3.5-35B-A3BAlibaba

60.0%

10

Qwen3-235B-A22BAlibaba

50.2%

22 models total