Model comparison
Llama 4 Scout vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 27.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
StepFunSummary
- They share 17 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Step 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3 leads 40.1 to 20.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 36.9% for Llama 4 Scout and 62.3% for Step 3.
Side by side
| Llama 4 Scout | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 27.7 | 40.5 |
| Released | 2025-04-05 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Llama 4 Scout: 20.2 (#339), Step 3: 40.1 (#147)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Coding | 1286 | 1367 |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Step 3: —
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Step 3 leads
Llama 4 Scout: 9.1 (#345), Step 3: 28.4 (#105)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 62.3% |
| LMArena Hard Prompts | 1266 | 1355 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Step 3 leads
Llama 4 Scout: 19.6 (#286), Step 3: 37.6 (#148)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Math | 1287 | 1366 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Step 3 leads
Llama 4 Scout: 31.9 (#217), Step 3: 36.8 (#164)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Expert | 1235 | 1333 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Step 3 leads
Llama 4 Scout: 32.2 (#102), Step 3: 35.5 (#86)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Vision | 1118 | 1177 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Step 3 leads
Llama 4 Scout: 41.0 (#212), Step 3: 46.3 (#159)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Non-English | 1252 | 1327 |
| LMArena Chinese | 1255 | 1397 |
| LMArena German | 1272 | 1371 |
| LMArena Korean | 1207 | 1269 |
| LMArena Russian | 1263 | 1331 |
| LMArena Spanish | 1278 | 1371 |
| LMArena French | 1282 | — |
| LMArena Japanese | 1206 | — |
Instruction Following Step 3 leads
Llama 4 Scout: 65.8 (#217), Step 3: 70.4 (#164)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1332 |
| IFEval | 81.8% | — |
Long Context Step 3 leads
Llama 4 Scout: 27.5 (#294), Step 3: 40.3 (#157)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Longer Query | 1265 | 1326 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Step 3 leads
Llama 4 Scout: 37.0 (#261), Step 3: 54.3 (#151)
| Benchmark | Llama 4 Scout | Step 3 |
|---|---|---|
| LMArena Text | 1279 | 1350 |
| LMArena Creative Writing | 1249 | 1321 |
| LMArena Multi-Turn | 1280 | 1341 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 27.7 on the Noometry Index.
Is Llama 4 Scout or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and Step 3 share?
17 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Step 3 has 17.