ChLogic: leaderboard
Large language models perform increasingly well on standardized logical reasoning benchmarks, but whether this ability remains robust beyond English is unclear. We introduce ChLogic, an English--Chinese aligned benchmark that tests whether models preserve logical reasoning performance when the same latent logical structure is expressed in English and diverse Chinese surface realizations. Built fro
Metric: English (self-reported). Source: benchmarklist.com. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 14B | 99.13 | #537 |
| 2 | Qwen 3 32B | 99.07 | #443 |
| 3 | Qwen 3 8B | 98.4 | #674 |
| 4 | GLM-5.1 | 98.3 | #97 |
| 5 | Ministral 8B | 92.03 | #1040 |
| 6 | Qwen 3 0.6B | 78.3 | #1459 |
| 7 | Ministral 3B | 73.3 | #1278 |
Interactive version: theaggregate.ai/benchmark?slug=chlogic · How It Works · Data refreshed daily, snapshot 2026-10-20.