ReLE - Education - Gaokao: leaderboard
ReLE Chinese LLM benchmark (NoneLinear, formerly CLiB), a continuously updated Chinese-language evaluation run through each model's API. Education sub-dimension: questions from China's national college entrance examination (gaokao) across subjects. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Around August 2027. 148 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 68.7 | #9 |
| 2 | Kimi K3.1 Pro | 68.2 | #17 |
| 3 | Gemini 3.1 Pro (Preview) | 67.8 | #64 |
| 4 | Claude Opus 5 | 67.4 | #16 |
| 5 | Seed 2.0 Pro | 66.6 | #122 |
| 6 | Claude Opus 5.5 | 66.4 | #3 |
| 7 | Claude Opus 4.6 | 65.4 | #67 |
| 8 | GLM-5.3 Flash | 65.2 | #77 |
| 9 | Hy4 preview | 64.9 | #45 |
| 10 | DeepSeek V4 Pro | 64.7 | #112 |
| 11 | Kimi K3 | 63.9 | #35 |
| 12 | Kimi K2.7 Code | 63.6 | #95 |
| 13 | Gemini 3.8 Flash | 63.5 | #30 |
| 14 | Gemini 3.7 Flash | 63 | #24 |
| 15 | Qwen 3.8 Flash | 62.7 | #62 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-education-gaokao · How It Works · Data refreshed daily, snapshot 2026-11-05.