Model comparison
Llama 13b vs Llama 3.2 90B
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 24.4 on the Noometry Index.
Last verified . 2 shared benchmarks.
MetaSummary
- They share 2 benchmarks with published results for both. Llama 13b scores higher in 1 category and Llama 3.2 90B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 13b leads 26.7 to 11.1.
Side by side
| Llama 13b | Llama 3.2 90B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 24.4 | 27.5 |
| Released | 2023-02-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 13b: 21.4 (#337), Llama 3.2 90B: —
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| LMArena Coding | 683 | — |
Agentic & Tool Use Not comparable
Llama 13b: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning Llama 3.2 90B leads
Llama 13b: 14.0 (#329), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 100.58 | 125.5 |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 728 | — |
| 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 90B: 11.1 (#308)
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 838 | — |
| MATH Level 5 | — | 39.4% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Llama 3.2 90B: 21.7 (#274)
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| MMLU | 47.7% | 80.3% |
| GPQA Diamond | — | 41% |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
| ScienceQA | 43.3% | — |
Multilingual Not comparable
Llama 13b: 16.6 (#297), Llama 3.2 90B: —
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 819 | — |
Instruction Following Not comparable
Llama 13b: 36.7 (#305), Llama 3.2 90B: —
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 781 | — |
Writing & Preference Not comparable
Llama 13b: 13.8 (#312), Llama 3.2 90B: —
| Benchmark | Llama 13b | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 834 | — |
| LMArena Creative Writing | 794 | — |
| LMArena Multi-Turn | 753 | — |
Frequently asked questions
Is Llama 13b better than Llama 3.2 90B?
Llama 3.2 90B is the stronger model overall, scoring 27.5 to 24.4 on the Noometry Index.
How many benchmarks do Llama 13b and Llama 3.2 90B share?
2 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 3.2 90B has 9.