Meta
Llama 3.2 1B benchmark results
6 results on 6 benchmarks from 5 sources.
Open weights Released: Sep 24, 2024 Updated Oct 22, 2026
Also listed as: llama-3.2-1b-instruct · Llama-3.2-1B-Instruct · Llama-3.2-1B-Instruct (FC) · Llama-3.2-1B · meta-llama/Llama-3.2-1B-Instruct · meta-llama/Llama-3.2-1B
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1111 | 396 | Overall, style control on; 8045 votes; 95% CI 1103–1119“llama-3.2-1b-instruct” | Official leaderboard | Oct 8, 2026 |
| Open LLM Leaderboard v2 | 14.4% | 3366 | Average of 6 normalised benchmarks; bfloat16; 1.24B params“meta-llama/Llama-3.2-1B-Instruct” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 23.9% | 276 | Epoch AI run, accuracy | Independent run | Aug 30, 2026 |
| MMLU-Pro | 11.9% | 242 | Overall accuracy; data source: TIGER-Lab; 1B“Llama-3.2-1B” | Official leaderboard | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 0.6% | 260 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 30, 2026 |
| BFCL v4 (function calling) | 10.8% | 107 | Overall accuracy; native function calling (FC)“Llama-3.2-1B-Instruct (FC)” | Official leaderboard | Oct 17, 2026 |
FAQ
Where do these Llama 3.2 1B scores come from?
From Epoch AI Benchmarking Hub, Berkeley Function Calling Leaderboard (BFCL), LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.