LongCat-Flash-2512: benchmark results
Provider: Meituan. Access: API.
Aggregate Rating 1644 ± 21, rank #665 of 10916 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AGI-Eval Community - Subject Reasoning (Chinese) | 87.43 | Accuracy (%) | 71 |
| AGI-Eval Community - Subject Reasoning | 84.54 | Accuracy (%) | 65.7 |
| AGI-Eval Community - Subject Reasoning (English) | 83.26 | Accuracy (%) | 60.9 |
| AGI-Eval Community - Subject Knowledge | 84.55 | Accuracy (%) | 60 |
| AGI-Eval Community - Learning (Chinese) | 79.08 | Accuracy (%) | 56.5 |
| AGI-Eval Community - Mathematical Reasoning | 75.62 | Accuracy (%) | 56.4 |
| AGI-Eval Community - Objective Accuracy (English) | 86.82 | Accuracy (%) | 55.8 |
| AGI-Eval Community - Cognition (English) | 78.89 | Accuracy (%) | 50 |
| AGI-Eval Community - General Reasoning | 96.09 | Accuracy (%) | 50 |
| AGI-Eval Community - Interaction (Chinese) | 74.86 | Accuracy (%) | 47.1 |
| AGI-Eval Community - Learning | 84.94 | Accuracy (%) | 47.1 |
| AGI-Eval Community - Cognition | 76.61 | Accuracy (%) | 45 |
Interactive version: theaggregate.ai/model?slug=longcat-flash-2512 · How It Works · Data refreshed daily, snapshot 2026-11-08.