Llama 3.2 11B: benchmark results
Provider: Meta. Released 2024-09-25. Access: Open.
Unified ELO 1389 ± 13, rank #1241 of 1629 rated models, from 608 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MEGA-Bench Task - Bridge Strategies Expert | 47.1 | Task Score (%) | 100 |
| MEGA-Bench Task - Graph Hamiltonian Path | 48.2 | Task Score (%) | 100 |
| MEGA-Bench Task - Red Teaming Celebrity | 90 | Task Score (%) | 98.8 |
| MEGA-Bench Task - Constrained Generation Xor Images | 100 | Task Score (%) | 98.1 |
| MEGA-Bench Task - Bridge Strategies World-Class | 44.3 | Task Score (%) | 97.7 |
| MEGA-Bench Task - MMSoc Memotion | 68.2 | Task Score (%) | 96.5 |
| MEGA-Bench Task - Multiview Reasoning Camera Moving | 64.3 | Task Score (%) | 88.4 |
| MEGA-Bench Task - MFC Bench Check Clip Stable Diffusion Generate | 57.1 | Task Score (%) | 82.7 |
| MEGA-Bench Task - Number Comparison | 100 | Task Score (%) | 82.6 |
| MEGA-Bench Task - Video Camera Motion Description | 28.6 | Task Score (%) | 82.6 |
| MEGA-Bench Task - Bridge Strategies Advanced | 22.9 | Task Score (%) | 80.2 |
| MEGA-Bench Task - Visual Prediction Rater Novel View Synthesis | 14.3 | Task Score (%) | 79.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-2-11b · How It Works · Data refreshed daily, snapshot 2026-10-07.