MetaMath-13B-V1.0: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1298 ± 33, rank #8758 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 28.51 | Accuracy (%) (5-shot) | 46 |
| Open LLM Leaderboard v1 - WinoGrande | 72.45 | Accuracy (%) (5-shot) | 29.1 |
| Open LLM Leaderboard v1 - HellaSwag | 76.48 | Normalized accuracy (%) (10-shot) | 28.8 |
| Open LLM Leaderboard v1 - MMLU | 47.74 | Accuracy (%) (5-shot) | 26.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.49 | Normalized accuracy (%) (25-shot) | 24 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.58 | MC2 (%) (0-shot) | 17.5 |
| MATH-Perturb (Hard) | 5.73 | Accuracy (%) | 0 |
Interactive version: theaggregate.ai/model?slug=metamath-13b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.