ReLE - Education - High School Subjects: leaderboard
ReLE Chinese LLM benchmark (NoneLinear, formerly CLiB), a continuously updated Chinese-language evaluation run through each model's API. Education sub-dimension: high school subject exam questions (Chinese, mathematics, sciences, humanities, English). Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Around February 2027. 148 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 79.3 | #9 |
| 2 | Gemini 3.1 Pro (Preview) | 78.1 | #64 |
| 3 | Claude Opus 5 | 77.4 | #16 |
| 4 | Gemini 3.8 Flash | 77.2 | #30 |
| 5 | Qwen 3.7 Max | 77.2 | #85 |
| 6 | Gemini 3.7 Flash | 76.5 | #24 |
| 7 | Kimi K3.1 Pro | 75.5 | #17 |
| 8 | Claude Opus 5.5 | 75.1 | #3 |
| 9 | Seed 2.0 Pro | 74.9 | #122 |
| 10 | Gemini 3.5 Flash | 74.7 | #66 |
| 11 | DeepSeek V4.1 Flash | 74 | #37 |
| 12 | Hy4 preview | 74 | #45 |
| 13 | Kimi K3 | 73.8 | #35 |
| 14 | GPT-6 Astra | 73.7 | #6 |
| 15 | Qwen 3.8 Flash | 73.5 | #62 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-education-high-school-subjects · How It Works · Data refreshed daily, snapshot 2026-11-05.