Llama 3.2 3B Instruct

Llama / Meta

27scores
22benchmarks
$0 / $0 per 1M tokenscost in/out

Metadata

Llama Open source

Aliases: llama-3.2-3b-instruct, llama-3.2-3b-instruct:free, meta-llama-llama-3.2-3b-instruct, meta-llama/llama-3.2-3b-instruct, meta-llama/llama-3.2-3b-instruct:free

Benchmark Results

Benchmark Category Rank Score Sampled
Berkeley Function-Calling Leaderboard Agentic 98 21.95% 2026-05-27
UAVBench Agentic 26 62 2026-05-06
OpenUGI Alignment 1203 7.16 2026-05-06
Stick To Your Role! Alignment 22 0.49 2026-05-06
BTZSC Classification 31 43.02 2026-05-06
BigCodeBench Coding 116 23.40 2026-05-06
MathTutorBench Education 5 0.4689 2026-05-27
Open LLM Leaderboard v2 General Knowledge 1768 24.20 2026-05-06
HealthBench Hard Healthcare 40 0.26 2026-05-27
MuSR Intelligence 4368 1.37 2026-05-06
AraGen v3 Language 58 14.99 2026-05-06
La Leaderboard Language 21 23.15 2026-05-06
Open Arabic LLM Leaderboard Language 133 41.06 2026-05-06
Open Japanese LLM Leaderboard Language 560 41.11 2026-05-06
Open Japanese LLM Leaderboard Language 778 20.42 2026-05-06
Open Portuguese LLM Leaderboard Language 566 75.05 2026-05-06
MATH Level 5 Math 1515 17.67 2026-05-06
BRIDGE Medical Leaderboard Medical 177 34.81 2026-05-27
BRIDGE Medical Leaderboard Medical 274 22.9 2026-05-27
BRIDGE Medical Leaderboard Medical 281 21.6 2026-05-27
MEDIC Benchmark Medical 82 51.44 average normalized public table score 2026-05-27
LatamBoard Multilingual 32 54.73 2026-05-06
JSONSchemaBench Structured Output 10 88.3% schema compliance 2026-05-28
JSONSchemaBench Structured Output 28 65.3% schema compliance 2026-05-28
JSONSchemaBench Structured Output 40 32% schema compliance 2026-05-28
BFCL v2 Tool Use 4 0.67 2026-05-06
K-MetBench Weather 55 33.8% accuracy 2026-05-28