ReLE - Education - Primary 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: primary school subject exam questions. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Around March 2027. 148 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72 | #64 |
| 2 | Claude Opus 5 | 71.3 | #16 |
| 3 | GPT-6 Astra | 71.3 | #6 |
| 4 | Gemini 4 Argon | 71.3 | #9 |
| 5 | GPT-5.6 Pro Sol | 71.3 | #21 |
| 6 | Kimi K3 | 70.7 | #35 |
| 7 | Gemini 3.7 Flash | 70.7 | #24 |
| 8 | GPT-6.1 Sol | 70.7 | #7 |
| 9 | Claude Opus 4.8 (Thinking) | 70.7 | #39 (Claude Opus 4.8) |
| 10 | Gemini 3.8 Flash | 70 | #30 |
| 11 | Qwen 3.6 27B | 69.3 | #182 |
| 12 | Qwen 3.7 Max | 69.3 | #85 |
| 13 | Qwen 3.8 Max | 69.3 | #34 |
| 14 | Qwen 3.8 Flash | 69.3 | #62 |
| 15 | Gemini 3 Flash (Preview) | 68.7 | #90 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-education-primary-school-subjects · How It Works · Data refreshed daily, snapshot 2026-11-05.