Model comparison
Llama 2-13B vs Llama 3-70B
Llama 2-13B and Llama 3-70B score almost the same on the Noometry Index (29.6 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 2-13B scores higher in 2 categories and Llama 3-70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 31.1 to 12.8.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 54.2% for Llama 3-70B.
Side by side
| Llama 2-13B | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 29.6 | 28.8 |
| Released | 2023-07-18 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 2-13B: 30.9 (#291), Llama 3-70B: 35.8 (#218)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1062 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Llama 2-13B: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Llama 3-70B leads
Llama 2-13B: 12.8 (#337), Llama 3-70B: 18.0 (#288)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1195 |
| DTBench | 42.2% | 54.2% |
| Epoch Capabilities Index | 106.17 | 122.93 |
| WinoGrande | 72.8% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 57.1 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Llama 3-70B: 12.8 (#305)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Math | 1065 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
| GSM8K | 36.9% | — |
Knowledge Llama 2-13B leads
Llama 2-13B: 28.1 (#249), Llama 3-70B: 20.8 (#277)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1030 | 1149 |
| MMLU | 55.6% | 79.3% |
| GPQA Diamond | — | 40.6% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Llama 3-70B: —
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Llama 3-70B leads
Llama 2-13B: 26.5 (#279), Llama 3-70B: 33.6 (#251)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1024 | 1142 |
| LMArena Chinese | 1001 | 1114 |
| LMArena French | 1044 | 1232 |
| LMArena German | 1009 | 1169 |
| LMArena Japanese | 894 | 1017 |
| LMArena Korean | 953 | 1017 |
| LMArena Russian | 1055 | 1159 |
| LMArena Spanish | 1087 | 1241 |
Instruction Following Llama 3-70B leads
Llama 2-13B: 53.3 (#287), Llama 3-70B: 62.5 (#238)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1194 |
Long Context Llama 3-70B leads
Llama 2-13B: 32.3 (#269), Llama 3-70B: 35.6 (#240)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1064 | 1174 |
Writing & Preference Llama 3-70B leads
Llama 2-13B: 29.8 (#289), Llama 3-70B: 42.8 (#231)
| Benchmark | Llama 2-13B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1084 | 1221 |
| LMArena Creative Writing | 1047 | 1210 |
| LMArena Multi-Turn | 1050 | 1223 |
Frequently asked questions
Is Llama 2-13B better than Llama 3-70B?
Llama 2-13B and Llama 3-70B score almost the same on the Noometry Index (29.6 vs 28.8), so choose on price, context window or the category you care about most.
Is Llama 2-13B or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Llama 3-70B share?
21 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Llama 3-70B has 31.