pygmalion-6B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1243 ± 20, rank #2819 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 36.84 | Score | 22.9 |
| Open LLM Leaderboard v1 - GSM8K | 2.05 | Accuracy (%) (5-shot) | 19.2 |
| Open LLM Leaderboard v1 - HellaSwag | 67.47 | Normalized accuracy (%) (10-shot) | 18.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.53 | Normalized accuracy (%) (25-shot) | 16.8 |
| Open LLM Leaderboard v1 - WinoGrande | 62.51 | Accuracy (%) (5-shot) | 15.5 |
| Open LLM Leaderboard - IFEval | 20.91 | Score | 13.2 |
| Open LLM Leaderboard - BBH | 31.99 | Score | 11.9 |
| Open LLM Leaderboard v1 - MMLU | 25.73 | Accuracy (%) (5-shot) | 9.6 |
| Open LLM Leaderboard - MMLU-Pro | 11.84 | Score | 9.1 |
| Open LLM Leaderboard - MATH Level 5 | 0.83 | Score | 6 |
| Open LLM Leaderboard - GPQA | 24.92 | Score | 4.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 32.53 | MC2 (%) (0-shot) | 0.2 |
Interactive version: theaggregate.ai/model?slug=pygmalion-6b · How It Works · Data refreshed daily, snapshot 2026-09-23.