Model comparison
Llama 3.2 1B vs Llama 4 Scout
Llama 4 Scout is the stronger model overall, scoring 27.7 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.1× less per token, which makes it the better buy when Llama 4 Scout's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Llama 3.2 1B scores higher in 3 categories and Llama 4 Scout in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 7.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 43.1% for Llama 4 Scout.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.10 / $0.30 for Llama 4 Scout.
- Llama 4 Scout accepts more context: 128K tokens versus 60K.
Side by side
| Llama 3.2 1B | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 20.1 | 27.7 |
| Released | 2024-09-24 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 60K | 128K |
| Max output | 54K | 4K |
| Input $ / M tokens | $0.027 | $0.10 |
| Output $ / M tokens | $0.20 | $0.30 |
| Results tracked | 22 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.2 1B: 21.1 (#338), Llama 4 Scout: 20.2 (#339)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1070 | 1286 |
| BigCodeBench Complete | 11.3% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Instruct | 8.2% | — |
Agentic & Tool Use Llama 4 Scout leads
Llama 3.2 1B: 14.6 (#150), Llama 4 Scout: 24.6 (#119)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | 28.1% |
| BALROG | 6.6% | — |
Reasoning Llama 3.2 1B leads
Llama 3.2 1B: 16.2 (#308), Llama 4 Scout: 9.1 (#345)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1266 |
| Epoch Capabilities Index | 101.99 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |
Math Llama 4 Scout leads
Llama 3.2 1B: 10.4 (#313), Llama 4 Scout: 19.6 (#286)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 7.8% |
| LMArena Math | 1086 | 1287 |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Llama 4 Scout leads
Llama 3.2 1B: 7.2 (#312), Llama 4 Scout: 31.9 (#217)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 23.9% | 51.8% |
| LMArena Expert | 1007 | 1235 |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
Llama 3.2 1B: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 4 Scout leads
Llama 3.2 1B: 23.8 (#292), Llama 4 Scout: 41.0 (#212)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 973 | 1252 |
| LMArena Chinese | 959 | 1255 |
| LMArena German | 1014 | 1272 |
| LMArena Russian | 941 | 1263 |
| LMArena French | — | 1282 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Spanish | — | 1278 |
Instruction Following Llama 4 Scout leads
Llama 3.2 1B: 52.4 (#290), Llama 4 Scout: 65.8 (#217)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1031 | 1248 |
| IFEval | — | 81.8% |
Long Context Llama 3.2 1B leads
Llama 3.2 1B: 31.9 (#274), Llama 4 Scout: 27.5 (#294)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1050 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Llama 4 Scout leads
Llama 3.2 1B: 21.3 (#310), Llama 4 Scout: 37.0 (#261)
| Benchmark | Llama 3.2 1B | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1055 | 1279 |
| LMArena Creative Writing | 1033 | 1249 |
| EQ-Bench Creative Writing | 200 | 783 |
| LMArena Multi-Turn | 1030 | 1280 |
| WildBench | — | 78% |
Frequently asked questions
Is Llama 3.2 1B better than Llama 4 Scout?
Llama 4 Scout is the stronger model overall, scoring 27.7 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.1× less per token, which makes it the better buy when Llama 4 Scout's lead doesn't matter for your workload.
Which is cheaper, Llama 3.2 1B or Llama 4 Scout?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Llama 4 Scout lists at $0.10 and $0.30.
Is Llama 3.2 1B or Llama 4 Scout better for coding?
They score almost the same on coding (21.1 vs 20.2); test both on your own repository before choosing.
Which has the bigger context window?
Llama 4 Scout does, with 128K tokens against 60K.
How many benchmarks do Llama 3.2 1B and Llama 4 Scout share?
19 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Llama 4 Scout has 43.