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

OpenAI MRCR v2 8-needle 128K-256KLong context

Results for 8 models collected from 4 public sources.

#ModelScore

1

87.5%

2

79.3%

3

77.0%

4

Claude Opus 4.7Anthropic

59.2%

5

GPT-5.4 miniOpenAI

33.6%

6

GPT-5.4 nanoOpenAI

33.1%

7

29.6%

8

GPT-5 miniOpenAI

19.4%

8 models total