Model comparison
Llama 4 Maverick vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Meta
StepFunSummary
- They share 16 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 10.1.
- The biggest single-benchmark swing is SciCode: 33.1% for Llama 4 Maverick and 58.9% for Step 5 Preview.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 30.9 | 47.9 |
| Released | 2025-04-05 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.19 | $1 |
| Output $ / M tokens | $0.65 | $2.70 |
| Results tracked | 54 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Llama 4 Maverick: 26.6 (#324), Step 5 Preview: 51.8 (#36)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| SciCode | 33.1% | 58.9% |
| LMArena Coding | 1302 | 1480 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| LMArena WebDev | — | 1564 |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Step 5 Preview: —
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Step 5 Preview leads
Llama 4 Maverick: 10.1 (#342), Step 5 Preview: 40.0 (#57)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| LMArena Hard Prompts | 1281 | 1465 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Step 5 Preview leads
Llama 4 Maverick: 26.0 (#262), Step 5 Preview: 46.1 (#72)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Math | 1299 | 1470 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| ProofBench | — | 42% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Step 5 Preview leads
Llama 4 Maverick: 33.4 (#204), Step 5 Preview: 41.2 (#112)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1259 | 1470 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Step 5 Preview leads
Llama 4 Maverick: 31.6 (#105), Step 5 Preview: 41.0 (#41)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1142 | 1267 |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Step 5 Preview leads
Llama 4 Maverick: 42.2 (#195), Step 5 Preview: 53.8 (#54)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1269 | 1432 |
| LMArena Chinese | 1277 | 1519 |
| LMArena Russian | 1286 | 1436 |
| LMArena Spanish | 1293 | 1439 |
| LMArena French | 1259 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
Instruction Following Step 5 Preview leads
Llama 4 Maverick: 71.7 (#146), Step 5 Preview: 76.0 (#50)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1267 | 1444 |
| IFEval | 90.8% | — |
Long Context Step 5 Preview leads
Llama 4 Maverick: 31.4 (#279), Step 5 Preview: 44.5 (#64)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1280 | 1455 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Step 5 Preview leads
Llama 4 Maverick: 38.8 (#252), Step 5 Preview: 62.8 (#71)
| Benchmark | Llama 4 Maverick | Step 5 Preview |
|---|---|---|
| LMArena Text | 1287 | 1442 |
| LMArena Creative Writing | 1267 | 1410 |
| LMArena Multi-Turn | 1289 | 1447 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Step 5 Preview?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Llama 4 Maverick or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 128K.
How many benchmarks do Llama 4 Maverick and Step 5 Preview share?
16 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Step 5 Preview has 18.