llama_sft_longer: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1311 ± 34, rank #8521 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 14.94 | Accuracy (%) (5-shot) | 36.9 |
| Open LLM Leaderboard v1 - HellaSwag | 78.58 | Normalized accuracy (%) (10-shot) | 34.7 |
| Open LLM Leaderboard v1 - WinoGrande | 73.88 | Accuracy (%) (5-shot) | 33.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 54.78 | Normalized accuracy (%) (25-shot) | 32 |
| Open LLM Leaderboard v1 - MMLU | 46.87 | Accuracy (%) (5-shot) | 25.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.82 | MC2 (%) (0-shot) | 15.4 |
Interactive version: theaggregate.ai/model?slug=llama-sft-longer · How It Works · Data refreshed daily, snapshot 2026-11-08.