LLAMA-13B-test-finetuning: benchmark results
Provider: Meta.
Aggregate Rating 1354 ± 33, rank #7602 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.36 | Normalized accuracy (%) (10-shot) | 50.7 |
| Open LLM Leaderboard v1 - WinoGrande | 76.72 | Accuracy (%) (5-shot) | 50.1 |
| Open LLM Leaderboard v1 - GSM8K | 22.52 | Accuracy (%) (5-shot) | 42.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.02 | Normalized accuracy (%) (25-shot) | 38.7 |
| Open LLM Leaderboard v1 - MMLU | 54.27 | Accuracy (%) (5-shot) | 33.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.14 | MC2 (%) (0-shot) | 26.1 |
Interactive version: theaggregate.ai/model?slug=llama-13b-test-finetuning · How It Works · Data refreshed daily, snapshot 2026-11-08.