ReLE - Education: leaderboard
ReLE Chinese LLM benchmark (NoneLinear, formerly CLiB), a continuously updated Chinese-language evaluation run through each model's API. Education domain: gaokao questions and primary, middle and high school subject exams. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Around July 2027. 148 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 69.3 | #9 |
| 2 | Gemini 3.1 Pro (Preview) | 68.6 | #64 |
| 3 | Claude Opus 5 | 67.7 | #16 |
| 4 | Gemini 3.8 Flash | 67 | #30 |
| 5 | Gemini 3.7 Flash | 67 | #24 |
| 6 | Kimi K3.1 Pro | 67 | #17 |
| 7 | Seed 2.0 Pro | 65.9 | #122 |
| 8 | Kimi K3 | 65.7 | #35 |
| 9 | Qwen 3.7 Max | 65.4 | #85 |
| 10 | Gemini 3.5 Flash | 64.9 | #66 |
| 11 | Qwen 3.8 Flash | 64.9 | #62 |
| 12 | GPT-6 Astra | 64.6 | #6 |
| 13 | GLM-5.3 Flash | 64.2 | #77 |
| 14 | Qwen 3.8 Max | 63.7 | #34 |
| 15 | Gemini 3 Flash (Preview) | 63.5 | #90 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-education · How It Works · Data refreshed daily, snapshot 2026-11-05.