Alpaca_refine_gpt2_e1_se0: benchmark results
Provider: Other.
Aggregate Rating 1120 ± 37, rank #10512 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 26.51 | Accuracy (%) (5-shot) | 12.7 |
| Open LLM Leaderboard v1 - WinoGrande | 55.88 | Accuracy (%) (5-shot) | 9.4 |
| Open LLM Leaderboard v1 - HellaSwag | 45.39 | Normalized accuracy (%) (10-shot) | 9 |
| Open LLM Leaderboard v1 - ARC Challenge | 27.3 | Normalized accuracy (%) (25-shot) | 6.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.28 | MC2 (%) (0-shot) | 5.4 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=alpaca-refine-gpt2-e1-se0 · How It Works · Data refreshed daily, snapshot 2026-11-08.