Model comparison
Llama 3.1-405B vs Llama 3.2 3B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Llama 3.1-405B scores higher in 7 categories and Llama 3.2 3B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-405B leads 40.7 to 26.2.
Side by side
| Llama 3.1-405B | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.7 | 28.9 |
| Released | 2024-07-23 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1291 | 1098 |
| WeirdML | 21.4% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
Agentic & Tool Use Too close to call
Llama 3.1-405B: 21.0 (#140), Llama 3.2 3B: 20.1 (#143)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
| BALROG | — | 10.1% |
Reasoning Llama 3.2 3B leads
Llama 3.1-405B: 16.8 (#300), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1095 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Llama 3.2 3B leads
Llama 3.1-405B: 18.4 (#290), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1281 | 1126 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Too close to call
Llama 3.1-405B: 30.4 (#227), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1243 | 1090 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1248 | 1019 |
| LMArena Chinese | 1242 | 1017 |
| LMArena German | 1252 | 1056 |
| LMArena Russian | 1265 | 949 |
| LMArena French | 1279 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1259 | 1089 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1266 | 1100 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Llama 3.1-405B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1284 | 1110 |
| LMArena Creative Writing | 1262 | 1094 |
| EQ-Bench Creative Writing | 870 | 595 |
| LMArena Multi-Turn | 1297 | 1105 |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Llama 3.2 3B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.9 on the Noometry Index.
Is Llama 3.1-405B or Llama 3.2 3B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Llama 3.2 3B share?
14 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Llama 3.2 3B has 18.