Hunyuan 2.0: benchmark results
Provider: Tencent.
Aggregate Rating 1638 ± 28, rank #701 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| KDR-Bench - Key Point Coverage | 46.7 | Key point coverage (%): share of the 261 annotated table-gro | 50 |
| KDR-Bench - Main Conclusion Alignment | 61 | Main conclusion alignment (0-100): a 0-10 judge score of how | 37.5 |
| ClawProBench | 52.69 | Final Score (imported) | 35.7 |
| OneMillion-Bench | 8.5 | Pass Rate (%) | 28.1 |
| OneMillion-Bench (CN) - Expert Score | 36.3 | Expert score (%): per task, the weighted share of expert-wri | 20 |
| OneMillion-Bench - Expert Score | 34.7 | Expert score (%): per task, the weighted share of expert-wri | 20 |
| OneMillion-Bench (CN) | 9.5 | Pass rate (%): share of tasks whose expert score reaches the | 13.3 |
| OneMillion-Bench (CN, Web Search) | 6.5 | Pass rate (%): share of tasks whose expert score reaches the | 8.3 |
| OneMillion-Bench (CN, Web Search) - Expert Score | 32.8 | Expert score (%): per task, the weighted share of expert-wri | 5.6 |
| KDR-Bench | 40.6 | RACE general-purpose score (0-100): equal-weight mean of com | 0 |
| OneMillion-Bench (Web Search) | 3 | Pass rate (%): share of tasks whose expert score reaches the | 0 |
| OneMillion-Bench (Web Search) - Expert Score | 30.2 | Expert score (%): per task, the weighted share of expert-wri | 0 |
Interactive version: theaggregate.ai/model?slug=hunyuan-2-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.