Hunyuan-T1: benchmark results
Provider: Tencent.
Aggregate Rating 1602 ± 24, rank #989 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM2014 Logic 2025-03 | 51.34 | Median Score | 50 |
| AGI-Eval Community - Learning (English) | 89.33 | Accuracy (%) | 47.1 |
| AGI-Eval Community - Learning (Chinese) | 77.12 | Accuracy (%) | 44.6 |
| AGI-Eval Community - Learning | 84.19 | Accuracy (%) | 40.7 |
| AGI-Eval Community - Cognition (English) | 78.02 | Accuracy (%) | 39.9 |
| AGI-Eval Community - Mathematical Reasoning | 68.25 | Accuracy (%) | 37.1 |
| AGI-Eval Community - Subject Reasoning (Chinese) | 77.11 | Accuracy (%) | 37 |
| AGI-Eval Community - Subject Knowledge | 80.72 | Accuracy (%) | 36.4 |
| AGI-Eval Community - Interaction (Chinese) | 72.52 | Accuracy (%) | 34.8 |
| AGI-Eval Community - Interaction (English) | 88.19 | Accuracy (%) | 34.8 |
| AGI-Eval Community - Interaction | 76.63 | Accuracy (%) | 33.6 |
| AGI-Eval Community - General Reasoning | 94.5 | Accuracy (%) | 30 |
Interactive version: theaggregate.ai/model?slug=hunyuan-t1 · How It Works · Data refreshed daily, snapshot 2026-11-08.