Model comparison
Llama 3.2 3B vs Llama 4 Scout
Llama 3.2 3B and Llama 4 Scout score almost the same on the Noometry Index (28.4 vs 27.4), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
MetaSummary
- They share 16 benchmarks with published results for both. Llama 3.2 3B scores higher in 4 categories and Llama 4 Scout in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 4 Scout leads 41.3 to 26.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 43.1% for Llama 4 Scout.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.10 / $0.30 for Llama 4 Scout.
- Llama 3.2 3B accepts more context: 131K tokens versus 128K.
Side by side
| Llama 3.2 3B | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 28.4 | 27.4 |
| Released | 2024-09-24 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 118K | 4K |
| Input $ / M tokens | $0.05 | $0.10 |
| Output $ / M tokens | $0.33 | $0.30 |
| Results tracked | 18 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.2 3B leads
Llama 3.2 3B: 27.1 (#314), Llama 4 Scout: 19.9 (#334)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1098 | 1286 |
| BigCodeBench Complete | 28.3% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Instruct | 23.4% | — |
Agentic & Tool Use Llama 4 Scout leads
Llama 3.2 3B: 19.9 (#135), Llama 4 Scout: 24.4 (#109)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | 28.1% |
| BALROG | 10.1% | — |
Reasoning Llama 3.2 3B leads
Llama 3.2 3B: 20.1 (#225), Llama 4 Scout: 9.2 (#339)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1266 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| Epoch Capabilities Index | — | 129.64 |
| ForecastBench | — | 57.5 |
Math Llama 3.2 3B leads
Llama 3.2 3B: 29.9 (#213), Llama 4 Scout: 18.4 (#280)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Math | 1126 | 1286 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Llama 4 Scout leads
Llama 3.2 3B: 29.1 (#232), Llama 4 Scout: 31.8 (#208)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Expert | 1090 | 1236 |
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
Llama 3.2 3B: —, Llama 4 Scout: 31.6 (#98)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 4 Scout leads
Llama 3.2 3B: 26.4 (#276), Llama 4 Scout: 41.3 (#207)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1019 | 1253 |
| LMArena Chinese | 1017 | 1256 |
| LMArena German | 1056 | 1274 |
| LMArena Russian | 949 | 1263 |
| LMArena French | — | 1283 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1207 |
| LMArena Spanish | — | 1277 |
Instruction Following Llama 4 Scout leads
Llama 3.2 3B: 56.3 (#270), Llama 4 Scout: 66.0 (#212)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1089 | 1248 |
| IFEval | — | 81.8% |
Long Context Llama 3.2 3B leads
Llama 3.2 3B: 33.4 (#256), Llama 4 Scout: 27.5 (#289)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1101 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Llama 4 Scout leads
Llama 3.2 3B: 24.9 (#302), Llama 4 Scout: 37.1 (#256)
| Benchmark | Llama 3.2 3B | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1110 | 1279 |
| LMArena Creative Writing | 1094 | 1249 |
| EQ-Bench Creative Writing | 595 | 783 |
| LMArena Multi-Turn | 1105 | 1281 |
| WildBench | — | 78% |
Frequently asked questions
Is Llama 3.2 3B better than Llama 4 Scout?
Llama 3.2 3B and Llama 4 Scout score almost the same on the Noometry Index (28.4 vs 27.4), so choose on price, context window or the category you care about most.
Which is cheaper, Llama 3.2 3B or Llama 4 Scout?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Llama 4 Scout lists at $0.10 and $0.30.
Is Llama 3.2 3B or Llama 4 Scout better for coding?
Llama 3.2 3B scores higher on coding benchmarks: 27.1 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Llama 3.2 3B does, with 131K tokens against 128K.
How many benchmarks do Llama 3.2 3B and Llama 4 Scout share?
16 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Llama 4 Scout has 43.