Moonshot v1 32K: benchmark results
Provider: Moonshot. Access: API.
Aggregate Rating 1498 ± 27, rank #2382 of 10916 rated models, from 206 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Language - Creation - Chinese (CompassBench 2409) | 51.9 | Score (%) | 86.2 |
| OpenCompass Knowledge - Social Science - Chinese (CompassBench 2409) | 87.5 | Score (%) | 77.6 |
| OpenCompass Language - Dialogue - Chinese (CompassBench 2409) | 52.7 | Score (%) | 75.9 |
| OpenCompass LLM - Instruction Following - Chinese (CompassBench 2501) | 58.8 | Score (%) | 74.4 |
| OpenCompass Language - NLP - Chinese (CompassBench 2409) | 51 | Score (%) | 72.4 |
| OpenCompass Reasoning - Social - Chinese (CompassBench 2409) | 46.2 | Score (%) | 70.7 |
| OpenCompass Math - High School - Chinese (CompassBench 2411) | 52.8 | Score (%) | 69.7 |
| OpenCompass Knowledge - Engineering - English (CompassBench 2501) | 89 | Score (%) | 66.7 |
| OpenCompass Math - College - Chinese (CompassBench 2411) | 38.5 | Score (%) | 66.7 |
| OpenCompass Math - High School - English (CompassBench 2411) | 50.9 | Score (%) | 66.7 |
| OpenCompass Reasoning - Science and Engineering - Chinese (CompassBench 2409) | 48 | Score (%) | 65.5 |
| OpenCompass Agent - T-Eval - English (CompassBench 2409) | 86.3 | Score (%) | 62.1 |
Interactive version: theaggregate.ai/model?slug=moonshot-v1-32k · How It Works · Data refreshed daily, snapshot 2026-11-08.