Skip to content
The Aggregate

Unified LLM rankings, daily

Models Task Explorer Subscriptions What's New Trends Benchmarks Builder Guesswork
How It Works Daily brief
The Aggregate
Loading data...

OpenCompass Knowledge - Science - Chinese (CompassBench 2501): leaderboard

Metric: Score (%). Source: rank.opencompass.org.cn. 40 models tracked.

Top models

#ModelScore
1Claude 3.5 Sonnet (20241022)95
2DeepSeek R194
3O1 (2024-12-17)93
4GPT-4o (2024-11-20)93
5Gemini 2.0 Pro (Preview 02-05)93
6Llama 3.1 405B Instruct FP893
7DeepSeek V392
8O3 Mini (2025-01-31)92
9Qwen 2.5 Max92
10Llama 3.1 70B Instruct91
11Mistral Large 2 (Nov) Instruct (2411)91
12O1 Mini (2024-09-12)91
13Gemini 2.0 Flash (001)91
14QwQ 32B-Preview91
15Doubao-1.5-pro-32k-25011591

Interactive version: theaggregate.ai/benchmark?slug=opencompass-knowledge-science-chinese-compassbench-2501 · How It Works · Data refreshed daily, snapshot 2026-09-19.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.
A

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out