merge_dolly-v2-3b_dpo_test: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1158 ± 38, rank #9845 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 2.12 | Accuracy (%) (5-shot) | 19.4 |
| Open LLM Leaderboard v1 - HellaSwag | 65.14 | Normalized accuracy (%) (10-shot) | 17.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.02 | Normalized accuracy (%) (25-shot) | 16.3 |
| Open LLM Leaderboard v1 - WinoGrande | 59.35 | Accuracy (%) (5-shot) | 12.5 |
| Open LLM Leaderboard v1 - MMLU | 24.99 | Accuracy (%) (5-shot) | 6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 33.3 | MC2 (%) (0-shot) | 0.5 |
Interactive version: theaggregate.ai/model?slug=merge-dolly-v2-3b-dpo-test · How It Works · Data refreshed daily, snapshot 2026-11-08.