Model comparison
Llama 3.2 11B vs Llama 3.2 3B
Llama 3.2 3B has enough public results to be ranked (#318); Llama 3.2 11B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. Llama 3.2 11B scores higher in 1 category and Llama 3.2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in agentic & tool use, where Llama 3.2 11B leads 27.0 to 19.9.
- The biggest single-benchmark swing is BALROG: 16.8% for Llama 3.2 11B and 10.1% for Llama 3.2 3B.
Side by side
| Llama 3.2 11B | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 31.6 | 28.4 |
| Released | 2024-09-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 27.1 (#314)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| BigCodeBench Instruct | — | 23.4% |
| LMArena Coding | — | 1098 |
| BigCodeBench Complete | — | 28.3% |
Agentic & Tool Use Llama 3.2 11B leads
Llama 3.2 11B: 27.0, Llama 3.2 3B: 19.9 (#135)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| BALROG | 16.8% | 10.1% |
| Berkeley Function Calling Leaderboard | — | 21.9% |
Reasoning Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 20.1 (#225)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | — | 1095 |
Math Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 29.9 (#213)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | — | 1126 |
Knowledge Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 29.1 (#232)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | — | 1090 |
| MMLU | 56.5% | — |
Multimodal Not comparable
Llama 3.2 11B: 23.8, Llama 3.2 3B: —
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 966 | — |
Multilingual Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 26.4 (#276)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | — | 1019 |
| LMArena Chinese | — | 1017 |
| LMArena German | — | 1056 |
| LMArena Russian | — | 949 |
Instruction Following Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 56.3 (#270)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | — | 1089 |
Long Context Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 33.4 (#256)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | — | 1101 |
Writing & Preference Not comparable
Llama 3.2 11B: —, Llama 3.2 3B: 24.9 (#302)
| Benchmark | Llama 3.2 11B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | — | 1110 |
| LMArena Creative Writing | — | 1094 |
| EQ-Bench Creative Writing | — | 595 |
| LMArena Multi-Turn | — | 1105 |
Frequently asked questions
Is Llama 3.2 11B better than Llama 3.2 3B?
Llama 3.2 3B has enough public results to be ranked (#318); Llama 3.2 11B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.2 11B and Llama 3.2 3B share?
1 benchmark has published results for both models. Llama 3.2 11B has 3 scored results on Noometry and Llama 3.2 3B has 18.