Model comparison
Llama 2-70B vs Llama 3.2 1B
Llama 2-70B is the stronger model overall, scoring 24.1 to 19.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
MetaSummary
- They share 16 benchmarks with published results for both. Llama 2-70B scores higher in 6 categories and Llama 3.2 1B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 2-70B leads 32.5 to 21.4.
Side by side
| Llama 2-70B | Llama 3.2 1B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 24.1 | 19.9 |
| Released | 2023-07-18 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 60K |
| Max output | — | 54K |
| Input $ / M tokens | — | $0.027 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Llama 2-70B: 30.8 (#281), Llama 3.2 1B: 20.6 (#333)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1079 | 1071 |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |
Agentic & Tool Use Not comparable
Llama 2-70B: —, Llama 3.2 1B: 14.5 (#142)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10.8% |
| BALROG | — | 6.6% |
Reasoning Llama 3.2 1B leads
Llama 2-70B: 13.7 (#324), Llama 3.2 1B: 15.6 (#304)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1044 |
| Epoch Capabilities Index | 113.59 | 101.95 |
| Chess Puzzles | — | 0% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Llama 3.2 1B leads
Llama 2-70B: 7.5 (#320), Llama 3.2 1B: 9.7 (#308)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 0.6% |
| LMArena Math | 1091 | 1086 |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Too close to call
Llama 2-70B: 7.4 (#305), Llama 3.2 1B: 7.2 (#307)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 26.3% | 23.9% |
| LMArena Expert | 1039 | 1007 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Llama 2-70B leads
Llama 2-70B: 27.9 (#269), Llama 3.2 1B: 23.9 (#287)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1045 | 973 |
| LMArena Chinese | 994 | 958 |
| LMArena German | 1041 | 1014 |
| LMArena Russian | 1083 | 941 |
| LMArena French | 1089 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1142 | — |
Instruction Following Llama 2-70B leads
Llama 2-70B: 55.1 (#273), Llama 3.2 1B: 52.6 (#285)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1071 | 1031 |
Long Context Too close to call
Llama 2-70B: 32.2 (#265), Llama 3.2 1B: 31.9 (#269)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1062 | 1050 |
Writing & Preference Llama 2-70B leads
Llama 2-70B: 32.5 (#274), Llama 3.2 1B: 21.4 (#305)
| Benchmark | Llama 2-70B | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1115 | 1055 |
| LMArena Creative Writing | 1075 | 1033 |
| LMArena Multi-Turn | 1088 | 1030 |
| EQ-Bench Creative Writing | — | 200 |
Frequently asked questions
Is Llama 2-70B better than Llama 3.2 1B?
Llama 2-70B is the stronger model overall, scoring 24.1 to 19.9 on the Noometry Index.
Is Llama 2-70B or Llama 3.2 1B better for coding?
Llama 2-70B scores higher on coding benchmarks: 30.8 versus 20.6 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Llama 3.2 1B share?
16 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Llama 3.2 1B has 22.