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

v0.1.66.c14ade6abf77浙ICP备09076226号-7

Loading page content

Changelog

A record of feature, data, and experience improvements released to Leaderboard.cn users.

v0.1.562026-09-23

GPT-6 Sol and Luna

Added GPT-6 Sol and GPT-6 Luna with results across 12 and 9 official benchmarks respectively, including evaluation sources, reasoning effort, and API pricing. Report columns with mixed reasoning settings no longer show a single effort label.
Improved endpoint label alignment and spacing on the historical timeline to reduce overlap.

v0.1.552026-09-23

Claude Opus 5.5

Added Claude Opus 5.5 with model specifications, API pricing, and results across 18 official benchmarks, including comparisons with models in the same report.

v0.1.542026-09-22

Grok 4.7 and MiMo-V2.6

Added Grok 4.7, MiMo-V2.6-Pro, and MiMo-V2.6-Flash with model specifications, API pricing, and official benchmark results.

v0.1.532026-09-10

DeepSeek V4.1 Flash

Model specifications, API pricing, and official benchmark results are now available.

v0.1.522026-09-05

GPT-6 Astra

Added GPT-6 Astra specifications, API pricing, and official benchmark results.

v0.1.512026-09-03

Separate AutomationBench results

Public and private evaluation sets are now shown separately to keep comparisons consistent.

v0.1.502026-09-03

GLM-5.3 open weights and model updates

Added GLM-5.3 weight downloads, license details, and official deployment guides.
Updated Qwen3.8-Max-0902 official benchmark results and added Muse Spark 1.3 specifications, pricing, and evaluations.

v0.1.492026-09-03

Arena.ai leaderboard update

Refreshed Arena.ai rankings and corrected several model names and version mappings.

v0.1.482026-09-03

Gemini 3.8 Flash

Added specifications, API pricing, and official benchmark results, with promotional rates clearly labeled.

v0.1.472026-09-02

Claude Fable 5.1

Added specifications and official benchmark results, with Mythos 5.1 listed as an alias of the same model.
Removed model scores and ranking claims that could become outdated from benchmark descriptions.

1
3
4
5
6
7