llama-160m: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1199 ± 20, rank #2901 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 37.92 | Score | 29 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.08 | MC2 (%) (0-shot) | 19.2 |
| Open LLM Leaderboard - GPQA | 26.17 | Score | 15.6 |
| Open LLM Leaderboard v1 - GSM8K | 0.08 | Accuracy (%) (5-shot) | 9.5 |
| Open LLM Leaderboard - IFEval | 17.91 | Score | 9.2 |
| Open LLM Leaderboard v1 - HellaSwag | 35.23 | Normalized accuracy (%) (10-shot) | 7.1 |
| Open LLM Leaderboard - MATH Level 5 | 0.83 | Score | 6 |
| Open LLM Leaderboard - MMLU-Pro | 11.28 | Score | 4.4 |
| Open LLM Leaderboard v1 - WinoGrande | 50.83 | Accuracy (%) (5-shot) | 4.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 24.83 | Normalized accuracy (%) (25-shot) | 4.2 |
| Open LLM Leaderboard v1 - MMLU | 24.26 | Accuracy (%) (5-shot) | 3.4 |
| Open LLM Leaderboard - BBH | 28.88 | Score | 1.7 |
Interactive version: theaggregate.ai/model?slug=llama-160m · How It Works · Data refreshed daily, snapshot 2026-09-23.