ReLE - Agents and Tool Use: leaderboard
ReLE Chinese LLM benchmark (NoneLinear, formerly CLiB), a continuously updated Chinese-language evaluation run through each model's API. Agents and tool-use domain, ReLE's own runs of BFCL-V3 and TAU-bench style tasks. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: nonelinear.com. Saturation forecast: Not forecast. 134 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | MiniMax-M2.7 | 75.8 | #270 |
| 2 | Qwen 3.5 Plus | 73.7 | #133 |
| 3 | Gemini 4 Argon | 73.7 | #9 |
| 4 | Claude Opus 4.8 | 73.1 | #39 |
| 5 | GLM 4.5 Air | 73 | #403 |
| 6 | GLM-4.5 | 72.7 | #283 |
| 7 | GLM-5.1 | 71.7 | #109 |
| 8 | GLM-5.2 | 71.6 | #80 |
| 9 | Claude Opus 5.5 | 70.8 | #3 |
| 10 | Claude Fable 5 | 70.4 | #20 |
| 11 | GLM-4.6 | 69.9 | #265 |
| 12 | Step 3.7 Flash | 69.9 | #247 |
| 13 | Claude Opus 4.6 | 69.1 | #67 |
| 14 | Qwen 3.7 Max | 68.8 | #85 |
| 15 | Hy4 preview | 68.2 | #45 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=rele-agents-and-tool-use · How It Works · Data refreshed daily, snapshot 2026-11-05.