Hunyuan-1.8B-Pretrain: benchmark results

Provider: Tencent. Access: Open.

Aggregate Rating 1407 ± 35, rank #5939 of 10552 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - PAWS (English) (0-shot)71Accuracy (%), English benchmark100
Lara Mini Base Report (base-model protocol) - MBPP (3-shot)58.8pass@1 (execution) (%)93.5
Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot)62.2pass@1; must pass MBPP's own and the EvalPlus tests (%)92.6
Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot)39.6pass@1, direct prediction, official answer parser (%)86.1
Lara Mini Base Report (base-model protocol) - CRUXEval-O (2-shot)38.4pass@1, direct prediction, official answer parser (%)85.2
Lara Mini Base Report (base-model protocol) - PAWS-X, All Languages (0-shot)58.5Accuracy (%) averaged over all languages/variants of the ben82.4
Lara Mini Base Report (base-model protocol) - GSM8K (5-shot)71.6Exact match (strict extraction: first "#### N", else first \79.6
Lara Mini Base Report (base-model protocol) - MMLU-Pro (5 (CoT)-shot)37.5Exact match (%), English benchmark75.9
Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot)75.4Accuracy (%), English benchmark72.2
Lara Mini Base Report (base-model protocol) - MATH (4-shot)42.3Math-Verify equivalence, Minerva prompts, 5,000 problems ove70.4
Lara Mini Base Report (base-model protocol) - MGSM (8 (CoT)-shot)42.1Exact match on each language's native CoT answer phrase, ave68.5
Lara Mini Base Report (base-model protocol) - MMLU (5-shot)62.9Accuracy (%), English benchmark66.7

Interactive version: theaggregate.ai/model?slug=hunyuan-1-8b-pretrain · How It Works · Data refreshed daily, snapshot 2026-11-16.