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

Frontier Science ResearchReasoning

Results for 14 models collected from 2 public sources.

#ModelScore

1

GPT-5.4 ProOpenAI

36.7%

2

33.9%

3

33.0%

4

Claude Opus 4.8Anthropic

32.9%

5

Seed2.1 ProByteDance

28.3%

6

25.2%

7

Qwen3.7-MaxAlibaba

24.8%

8

Hunyuan 3Tencent

21.3%

9

DeepSeek-V4-ProDeepSeek

21.3%

10

GLM-5.2Zhipu AI

19.8%

14 models total