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

SuperGPQAReasoning

Official website

Results for 65 models collected from 13 public sources.

#ModelScore

1

Gemini 3.1 ProGoogle

76.6%

2

Gemini 3 ProGoogle

74.0%

3

Qwen3.7-MaxAlibaba

73.6%

4

72.7%

5

Claude Opus 4.6Anthropic

72.5%

6

Qwen3.6-PlusAlibaba

71.6%

7

Qwen3.7-PlusAlibaba

71.4%

8

Kimi-K2.6Moonshot AI

71.3%

9

Seed2.1 ProByteDance

70.8%

10

Claude Opus 4.5Anthropic

70.6%

65 models total