Llama 3.2 1B
Llama 3.2 1B places in the top three on Vectara Hallucination Leaderboard (HHEM).
Meta Released 24 Sep 2024 24
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Meta Sep 2024 Llama 3.2 1B
Open weights
No Epoch Capabilities Index score yet
- GPQA Diamond 23.9% #213 /219
- Vectara Hallucination Leaderboard (HHEM) 20.7% #3 /148
- BigCodeBench-Hard 1.00% #96 /96
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 20.7% | #3 of 148 | Official leaderboard | |
| ALRAGE | 43.1% | #35 of 39 | Official leaderboard | |
| ArbMMLU-HT | 23.9% | #35 of 39 | Official leaderboard | |
| MadinahQA | 25.7% | #35 of 39 | Official leaderboard | |
| AlGhafa | 33.9% | #37 of 39 | Official leaderboard | |
| LMArena (Elo) | 1,111 | #320 of 333 | Official leaderboard | |
| FaithJudge | 67.7% | #36 of 37 | Official leaderboard | |
| MMLU-Pro | 11.9% | #207 of 212 | Official leaderboard | |
| Creative Writing v3 | 31.9 | #120 of 120 | Official leaderboard | |
| EQ-Bench v2 | 22.6 | #85 of 85 | Official leaderboard | |
| EQ-Bench 3 | 200 | #78 of 78 | Official leaderboard | |
| WritingBench | 28.7 | #45 of 45 | Official leaderboard | |
| ArabicMMLU | 26.5% | #39 of 39 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 30.2% | #39 of 39 | Official leaderboard | |
| BuzzBench | 9.51 | #23 of 23 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 23.9% | #213 of 219 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 0.56% | #199 of 202 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 9.80% | #68 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 1.00% | #96 of 96 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 10.8% | #63 of 65 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 21.9% | #65 of 67 | Official leaderboard | |
| BALROG | 6.60% | #34 of 35 | Official leaderboard | |
| LisanBench | 3.67 | #133 of 133 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 37.1% | #35 of 39 | Official leaderboard |