Model comparison
Phi-4 Mini vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 11× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Microsoft
StepFunSummary
- They share 2 benchmarks with published results for both. Phi-4 Mini scores higher in 0 categories and Step 5 Preview in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 28.1.
- The biggest single-benchmark swing is SciCode: 10.8% for Phi-4 Mini and 58.9% for Step 5 Preview.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Phi-4 Mini | Step 5 Preview | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 30.9 | 47.9 |
| Released | 2024-12-11 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.075 | $1 |
| Output $ / M tokens | $0.30 | $2.70 |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Phi-4 Mini: 28.1 (#317), Step 5 Preview: 51.8 (#36)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| SciCode | 10.8% | 58.9% |
| LMArena WebDev | — | 1564 |
| LMArena Coding | — | 1480 |
Reasoning Step 5 Preview leads
Phi-4 Mini: 22.4 (#195), Step 5 Preview: 40.0 (#57)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| LMArena Hard Prompts | — | 1465 |
Math Not comparable
Phi-4 Mini: —, Step 5 Preview: 46.1 (#72)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
Knowledge Step 5 Preview leads
Phi-4 Mini: 25.3 (#262), Step 5 Preview: 41.2 (#112)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Phi-4 Mini: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Phi-4 Mini: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Phi-4 Mini: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Phi-4 Mini: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Phi-4 Mini: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Phi-4 Mini | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Phi-4 Mini better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 11× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Phi-4 Mini or Step 5 Preview?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Phi-4 Mini or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 28.1 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 Phi-4 Mini and Step 5 Preview share?
2 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Step 5 Preview has 18.