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

WideSearchAgents

Results for 18 models collected from 4 public sources.

#ModelScore

1

Kimi-K2.6Moonshot AI

80.8%

2

80.0%

3

Seed2.1 ProByteDance

76.4%

4

Hunyuan 3Tencent

76.4%

5

Claude Opus 4.5Anthropic

76.4%

6

GLM-5.1Zhipu AI

76.1%

7

DeepSeek-V4-ProDeepSeek

75.7%

8

DeepSeek-V4-FlashDeepSeek

74.3%

9

Qwen3.6-PlusAlibaba

74.3%

10

Qwen3.5-397B-A17BAlibaba

74.0%

18 models total