Model comparison
Llama 13b vs Llama 3.2 1B
Llama 13b is the stronger model overall, scoring 24.4 to 20.1 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 2 categories and Llama 3.2 1B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 13b leads 26.7 to 10.4.
Side by side
| Llama 13b | Llama 3.2 1B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 24.4 | 20.1 |
| Released | 2023-02-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 60K |
| Max output | — | 54K |
| Input $ / M tokens | — | $0.027 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 13b: 21.4 (#337), Llama 3.2 1B: 21.1 (#338)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 683 | 1070 |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |
Agentic & Tool Use Not comparable
Llama 13b: —, Llama 3.2 1B: 14.6 (#150)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10.8% |
| BALROG | — | 6.6% |
Reasoning Llama 3.2 1B leads
Llama 13b: 14.0 (#329), Llama 3.2 1B: 16.2 (#308)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1044 |
| Epoch Capabilities Index | 100.58 | 101.99 |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Llama 3.2 1B: 10.4 (#313)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Math | 838 | 1086 |
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Llama 3.2 1B: 7.2 (#312)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | — | 23.9% |
| LMArena Expert | — | 1007 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Llama 3.2 1B: —
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Llama 3.2 1B leads
Llama 13b: 16.6 (#297), Llama 3.2 1B: 23.8 (#292)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 819 | 973 |
| LMArena Chinese | — | 959 |
| LMArena German | — | 1014 |
| LMArena Russian | — | 941 |
Instruction Following Llama 3.2 1B leads
Llama 13b: 36.7 (#305), Llama 3.2 1B: 52.4 (#290)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 781 | 1031 |
Long Context Not comparable
Llama 13b: —, Llama 3.2 1B: 31.9 (#274)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | — | 1050 |
Writing & Preference Llama 3.2 1B leads
Llama 13b: 13.8 (#312), Llama 3.2 1B: 21.3 (#310)
| Benchmark | Llama 13b | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 834 | 1055 |
| LMArena Creative Writing | 794 | 1033 |
| LMArena Multi-Turn | 753 | 1030 |
| EQ-Bench Creative Writing | — | 200 |
Frequently asked questions
Is Llama 13b better than Llama 3.2 1B?
Llama 13b is the stronger model overall, scoring 24.4 to 20.1 on the Noometry Index.
Is Llama 13b or Llama 3.2 1B better for coding?
They score almost the same on coding (21.4 vs 21.1); test both on your own repository before choosing.
How many benchmarks do Llama 13b and Llama 3.2 1B share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 3.2 1B has 22.