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

τ³-BenchAgents

Results for 15 models collected from 3 public sources.

#ModelScore

1

DeepSeek-V4-FlashDeepSeek

73.7%

2

DeepSeek-V4-ProDeepSeek

73.2%

3

72.9%

4

Kimi-K2.6Moonshot AI

72.4%

5

Claude Opus 4.6Anthropic

72.4%

6

Qwen3.5-397B-A17BAlibaba

71.0%

7

Nemotron-3-UltraNVIDIA

70.9%

8

Qwen3.6-PlusAlibaba

70.7%

9

GLM-5.1Zhipu AI

70.6%

10

GLM-5Zhipu AI

69.2%

15 models total