MetaMath-Bagel-DPO-34B: benchmark results
Provider: Abacus.AI. Access: Open.
Aggregate Rating 1495 ± 35, rank #2435 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 76.54 | Accuracy (%) (5-shot) | 97.6 |
| Open LLM Leaderboard v1 - GSM8K | 72.18 | Accuracy (%) (5-shot) | 97.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 65.44 | MC2 (%) (0-shot) | 83.6 |
| Open LLM Leaderboard v1 - WinoGrande | 82.24 | Accuracy (%) (5-shot) | 83 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.17 | Normalized accuracy (%) (25-shot) | 79.6 |
| Open LLM Leaderboard v1 - HellaSwag | 84.23 | Normalized accuracy (%) (10-shot) | 64.7 |
Interactive version: theaggregate.ai/model?slug=metamath-bagel-dpo-34b · How It Works · Data refreshed daily, snapshot 2026-11-08.