Model comparison
Llama 3.2 3B vs Llama 3-70B
Llama 3.2 3B and Llama 3-70B score almost the same on the Noometry Index (28.9 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. Llama 3.2 3B scores higher in 3 categories and Llama 3-70B in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.2 3B leads 32.4 to 12.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 54.5% for Llama 3-70B.
Side by side
| Llama 3.2 3B | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 28.9 | 28.8 |
| Released | 2024-09-24 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3.2 3B: 27.6 (#319), Llama 3-70B: 35.8 (#218)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 43.6% |
| LMArena Coding | 1098 | 1206 |
| BigCodeBench Complete | 28.3% | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Llama 3-70B leads
Llama 3.2 3B: 20.1 (#143), Llama 3-70B: 21.1 (#139)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| Cybench | — | 5% |
| BALROG | 10.1% | — |
Reasoning Llama 3.2 3B leads
Llama 3.2 3B: 21.0 (#228), Llama 3-70B: 18.0 (#288)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Llama 3-70B: 12.8 (#305)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Math | 1126 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Llama 3-70B: 20.8 (#277)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1090 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
Llama 3.2 3B: 26.2 (#281), Llama 3-70B: 33.6 (#251)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1019 | 1142 |
| LMArena Chinese | 1017 | 1114 |
| LMArena German | 1056 | 1169 |
| LMArena Russian | 949 | 1159 |
| LMArena French | — | 1232 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Llama 3.2 3B: 56.0 (#275), Llama 3-70B: 62.5 (#238)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1194 |
Long Context Llama 3-70B leads
Llama 3.2 3B: 33.4 (#261), Llama 3-70B: 35.6 (#240)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1100 | 1174 |
Writing & Preference Llama 3-70B leads
Llama 3.2 3B: 24.7 (#307), Llama 3-70B: 42.8 (#231)
| Benchmark | Llama 3.2 3B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1110 | 1221 |
| LMArena Creative Writing | 1094 | 1210 |
| LMArena Multi-Turn | 1105 | 1223 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Llama 3-70B?
Llama 3.2 3B and Llama 3-70B score almost the same on the Noometry Index (28.9 vs 28.8), so choose on price, context window or the category you care about most.
Is Llama 3.2 3B or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Llama 3-70B share?
15 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Llama 3-70B has 31.