Model comparison
Llama 13b vs Llama 3-70B
Llama 3-70B is the stronger model overall, scoring 28.5 to 23.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
MetaSummary
- They share 11 benchmarks with published results for both. Llama 13b scores higher in 1 category and Llama 3-70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 43.0 to 13.9.
Side by side
| Llama 13b | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 23.9 | 28.5 |
| Released | 2023-02-24 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 13b: 20.9 (#332), Llama 3-70B: 35.3 (#215)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Coding | 683 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Llama 13b: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Llama 3-70B leads
Llama 13b: 13.4 (#327), Llama 3-70B: 17.4 (#284)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1195 |
| Epoch Capabilities Index | 100.09 | 122.91 |
| WinoGrande | 73% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| BIG-Bench Hard | 37.9% | — |
| ForecastBench | — | 57.1 |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
Math Llama 13b leads
Llama 13b: 24.4 (#259), Llama 3-70B: 12.0 (#299)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Math | 838 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Llama 3-70B: 20.8 (#272)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| MMLU | 47.7% | 79.3% |
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Llama 3-70B: —
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Llama 3-70B leads
Llama 13b: 16.8 (#292), Llama 3-70B: 33.8 (#246)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 819 | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Llama 13b: 36.9 (#300), Llama 3-70B: 62.8 (#233)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 781 | 1194 |
Long Context Not comparable
Llama 13b: —, Llama 3-70B: 35.6 (#235)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Llama 3-70B leads
Llama 13b: 13.9 (#307), Llama 3-70B: 43.0 (#225)
| Benchmark | Llama 13b | Llama 3-70B |
|---|---|---|
| LMArena Text | 834 | 1221 |
| LMArena Creative Writing | 794 | 1210 |
| LMArena Multi-Turn | 753 | 1223 |
Frequently asked questions
Is Llama 13b better than Llama 3-70B?
Llama 3-70B is the stronger model overall, scoring 28.5 to 23.9 on the Noometry Index.
Is Llama 13b or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 20.9 in the Noometry coding category.
How many benchmarks do Llama 13b and Llama 3-70B share?
11 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 3-70B has 31.