llama3.2:3B: benchmark results
Provider: Meta.
Aggregate Rating 1399 ± 50, rank #6138 of 10916 rated models, from 2 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ParsiEval | 34.34 | Accuracy (%, 364 questions) | 33.3 |
| ClaimDB: A Fact Verification Benchmark over Large Structured Data | 0.39 | Accuracy | 6.9 |
Interactive version: theaggregate.ai/model?slug=llama3-2-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.