chat_gpt2_dpo: benchmark results
Provider: Other. Access: Open.
Unified ELO 1198 ± 20, rank #2902 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 38.18 | Score | 30.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.26 | MC2 (%) (0-shot) | 16.6 |
| Open LLM Leaderboard - GPQA | 26.01 | Score | 13.2 |
| Open LLM Leaderboard v1 - HellaSwag | 31.22 | Normalized accuracy (%) (10-shot) | 6.1 |
| Open LLM Leaderboard - MMLU-Pro | 11.42 | Score | 5.9 |
| Open LLM Leaderboard v1 - MMLU | 24.95 | Accuracy (%) (5-shot) | 5.8 |
| Open LLM Leaderboard - MATH Level 5 | 0.53 | Score | 4.6 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 23.98 | Normalized accuracy (%) (25-shot) | 3.2 |
| Open LLM Leaderboard v1 - WinoGrande | 49.96 | Accuracy (%) (5-shot) | 2.7 |
| Open LLM Leaderboard - BBH | 29.02 | Score | 1.8 |
| Open LLM Leaderboard - IFEval | 9.86 | Score | 1.7 |
Interactive version: theaggregate.ai/model?slug=chat-gpt2-dpo · How It Works · Data refreshed daily, snapshot 2026-09-23.