Model comparison
Llama 13b vs Llama 2-70B
Llama 13b and Llama 2-70B score almost the same on the Noometry Index (24.4 vs 24.4), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. Llama 13b scores higher in 1 category and Llama 2-70B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 13b leads 26.7 to 8.1.
Side by side
| Llama 13b | Llama 2-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 24.4 | 24.4 |
| Released | 2023-02-24 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Llama 13b: 21.4 (#337), Llama 2-70B: 31.4 (#286)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Coding | 683 | 1079 |
Reasoning Too close to call
Llama 13b: 14.0 (#329), Llama 2-70B: 14.4 (#325)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1073 |
| BIG-Bench Hard | 37.9% | 64.9% |
| Epoch Capabilities Index | 100.58 | 113.79 |
| HellaSwag | 79.2% | 85.3% |
| LAMBADA | 75.2% | 78.9% |
| PIQA | 80.1% | 82.8% |
| WinoGrande | 73% | 80.2% |
| DTBench | — | 41.6% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Llama 2-70B: 8.1 (#326)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Math | 838 | 1091 |
| GSM8K | 20.6% | 69.6% |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
Knowledge Not comparable
Llama 13b: —, Llama 2-70B: 7.4 (#310)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 78.3% |
| BoolQ | 78.7% | 88.6% |
| MMLU | 47.7% | 69.9% |
| OpenBookQA | 56.4% | 60.2% |
| TriviaQA | 77.9% | 87.6% |
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
Multimodal Not comparable
Llama 13b: —, Llama 2-70B: —
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Llama 2-70B leads
Llama 13b: 16.6 (#297), Llama 2-70B: 27.7 (#274)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 819 | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Llama 2-70B leads
Llama 13b: 36.7 (#305), Llama 2-70B: 54.9 (#278)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 781 | 1071 |
Long Context Not comparable
Llama 13b: —, Llama 2-70B: 32.3 (#270)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Llama 2-70B leads
Llama 13b: 13.8 (#312), Llama 2-70B: 32.3 (#279)
| Benchmark | Llama 13b | Llama 2-70B |
|---|---|---|
| LMArena Text | 834 | 1115 |
| LMArena Creative Writing | 794 | 1075 |
| LMArena Multi-Turn | 753 | 1088 |
Frequently asked questions
Is Llama 13b better than Llama 2-70B?
Llama 13b and Llama 2-70B score almost the same on the Noometry Index (24.4 vs 24.4), so choose on price, context window or the category you care about most.
Is Llama 13b or Llama 2-70B better for coding?
Llama 2-70B scores higher on coding benchmarks: 31.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Llama 2-70B share?
20 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 2-70B has 35.