Loading data...
Hunyuan-4B-Pretrain: benchmark results
Provider: Tencent. Access: Open.
Aggregate Rating 1490 ± 37, rank #2455 of 10552 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot) | 56.3 | pass@1, direct prediction, official answer parser (%) | 100 |
| Lara Mini Base Report (base-model protocol) - CRUXEval-O (2-shot) | 57 | pass@1, direct prediction, official answer parser (%) | 100 |
| Lara Mini Base Report (base-model protocol) - MATH (4-shot) | 74.8 | Math-Verify equivalence, Minerva prompts, 5,000 problems ove | 100 |
| Lara Mini Base Report (base-model protocol) - MMLU-Pro (5 (CoT)-shot) | 55.1 | Exact match (%), English benchmark | 98.1 |
| Lara Mini Base Report (base-model protocol) - MGSM (8 (CoT)-shot) | 63.1 | Exact match on each language's native CoT answer phrase, ave | 96.3 |
| Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot) | 62.4 | pass@1; must pass MBPP's own and the EvalPlus tests (%) | 94.4 |
| Lara Mini Base Report (base-model protocol) - MBPP (3-shot) | 58.8 | pass@1 (execution) (%) | 93.5 |
| Lara Mini Base Report (base-model protocol) - PAWS-X, All Languages (0-shot) | 59.7 | Accuracy (%) averaged over all languages/variants of the ben | 93.5 |
| Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot) | 87.3 | Accuracy (%), English benchmark | 92.6 |
| Lara Mini Base Report (base-model protocol) - MMLU (5-shot) | 72.5 | Accuracy (%), English benchmark | 92.6 |
| Lara Mini Base Report (base-model protocol) - GSM8K (5-shot) | 78 | Exact match (strict extraction: first "#### N", else first \ | 90.7 |
| Lara Mini Base Report (base-model protocol) - Belebele, All Languages (0-shot) | 49 | Accuracy (%) averaged over all languages/variants of the ben | 88.9 |
Interactive version: theaggregate.ai/model?slug=hunyuan-4b-pretrain · How It Works · Data refreshed daily, snapshot 2026-11-16.