Model comparison
Llama 13b vs Llama 4 Scout
Llama 4 Scout is the stronger model overall, scoring 27.4 to 23.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 3 categories and Llama 4 Scout in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Scout leads 66.0 to 36.9.
Side by side
| Llama 13b | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 23.9 | 27.4 |
| Released | 2023-02-24 | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 21 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 13b: 20.9 (#332), Llama 4 Scout: 19.9 (#334)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 683 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Not comparable
Llama 13b: —, Llama 4 Scout: 24.4 (#109)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning Llama 13b leads
Llama 13b: 13.4 (#327), Llama 4 Scout: 9.2 (#339)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 728 | 1266 |
| Epoch Capabilities Index | 100.09 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| BIG-Bench Hard | 37.9% | — |
| ForecastBench | — | 57.5 |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Llama 13b leads
Llama 13b: 24.4 (#259), Llama 4 Scout: 18.4 (#280)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Math | 838 | 1286 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Llama 4 Scout: 31.8 (#208)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1236 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Llama 4 Scout: 31.6 (#98)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| ScienceQA | 43.3% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 4 Scout leads
Llama 13b: 16.8 (#292), Llama 4 Scout: 41.3 (#207)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 819 | 1253 |
| LMArena Chinese | — | 1256 |
| LMArena French | — | 1283 |
| LMArena German | — | 1274 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1207 |
| LMArena Russian | — | 1263 |
| LMArena Spanish | — | 1277 |
Instruction Following Llama 4 Scout leads
Llama 13b: 36.9 (#300), Llama 4 Scout: 66.0 (#212)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 781 | 1248 |
| IFEval | — | 81.8% |
Long Context Not comparable
Llama 13b: —, Llama 4 Scout: 27.5 (#289)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | — | 36% |
| LMArena Longer Query | — | 1265 |
Writing & Preference Llama 4 Scout leads
Llama 13b: 13.9 (#307), Llama 4 Scout: 37.1 (#256)
| Benchmark | Llama 13b | Llama 4 Scout |
|---|---|---|
| LMArena Text | 834 | 1279 |
| LMArena Creative Writing | 794 | 1249 |
| LMArena Multi-Turn | 753 | 1281 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
Frequently asked questions
Is Llama 13b better than Llama 4 Scout?
Llama 4 Scout is the stronger model overall, scoring 27.4 to 23.9 on the Noometry Index.
Is Llama 13b or Llama 4 Scout better for coding?
They score almost the same on coding (20.9 vs 19.9); test both on your own repository before choosing.
How many benchmarks do Llama 13b and Llama 4 Scout share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 4 Scout has 43.