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

LongBench v2Long context

Official website

Results for 22 models collected from 5 public sources.

#ModelScore

1

Qwen3.5-397B-A17BAlibaba

68.9%

2

Claude Opus 4.5Anthropic

64.4%

3

DeepSeek-V4-ProDeepSeek

62.1%

4

Qwen3.6-PlusAlibaba

62.0%

5

Nemotron-3-UltraNVIDIA

61.9%

6

Kimi-K2.5Moonshot AI

61.0%

7

GLM-5Zhipu AI

60.8%

8

Qwen3.5-27BAlibaba

60.6%

9

Qwen3.5-122B-A10BAlibaba

60.2%

10

Qwen3.5-35B-A3BAlibaba

59.0%

22 models total