CatunaMayo-DPO: benchmark results
Provider: Other. Access: Open.
Unified ELO 1504 ± 20, rank #1168 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 72.87 | Normalized accuracy (%) (25-shot) | 94 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.82 | MC2 (%) (0-shot) | 92.3 |
| Open LLM Leaderboard v1 - GSM8K | 70.2 | Accuracy (%) (5-shot) | 92.1 |
| Open LLM Leaderboard v1 - HellaSwag | 88.3 | Normalized accuracy (%) (10-shot) | 90.8 |
| Open LLM Leaderboard v1 - WinoGrande | 82.72 | Accuracy (%) (5-shot) | 85.2 |
| Open LLM Leaderboard v1 - MMLU | 65.24 | Accuracy (%) (5-shot) | 83.3 |
| Open LLM Leaderboard - MuSR | 44.5 | Score | 80.9 |
| Open LLM Leaderboard - BBH | 52.24 | Score | 60.5 |
| Open LLM Leaderboard - GPQA | 29.19 | Score | 46.9 |
| Open LLM Leaderboard - IFEval | 42.15 | Score | 43.4 |
| Open LLM Leaderboard - MMLU-Pro | 31.7 | Score | 42.8 |
| Open LLM Leaderboard - MATH Level 5 | 8.16 | Score | 41.4 |
Interactive version: theaggregate.ai/model?slug=catunamayo-dpo · How It Works · Data refreshed daily, snapshot 2026-09-23.