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

v0.1.53.364ac010a008浙ICP备09076226号-7

Loading page content

Changelog

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

v0.1.432026-08-17

Gemini 3.7 Flash

Added model specifications, API pricing, and official benchmark results.

v0.1.422026-08-15

Qwen3.8-27B

Added model specifications and official benchmark results.

v0.1.412026-08-14

GLM-5.3

Added release specifications and official benchmark results.

v0.1.402026-08-14

DeepSeek-V4-Pro-0813 update

Added model specifications, API pricing, and official benchmark results.

v0.1.392026-08-13

Qwen, DeepSeek, and Grok updates

Updated Qwen3.8 open models, DeepSeek-V4-Pro-0813, and Grok 4.6 specifications and scores, and refreshed Arena.ai rankings.
Aligned ranking rules across overall, open-weight, and local-deployment leaderboards.

v0.1.382026-08-12

Nemotron 3.5 Lightning

Added model specifications, open-weight information, and official benchmark results.

v0.1.372026-08-10

Muse Glimmer 30B

Added model specifications and official benchmark results.

v0.1.362026-08-03

Qwen3.8-Max benchmarks and pricing

Added release specifications, official benchmark results, and Alibaba Cloud API pricing.

v0.1.352026-07-31

DeepSeek-V4-Flash-0731 and rankings

Added open-weight information, API pricing, and official benchmark results.
The home leaderboard now shows each model version within a family.

v0.1.342026-07-31

GPT-5.6 specifications and pricing

Updated context and output limits for Sol, Terra, and Luna, and added Sol standard and fast-mode pricing.

1
3
4
5
6