Model comparison
Phi-4 Mini vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
StepFunSummary
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.6 to 25.3.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 128K.
Side by side
| Phi-4 Mini | Step 3.5 Flash | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 30.9 | 42.3 |
| Released | 2024-12-11 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 128K | 256K |
| Max output | 4K | 256K |
| Input $ / M tokens | $0.075 | $0.10 |
| Output $ / M tokens | $0.30 | $0.30 |
| Results tracked | 3 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Phi-4 Mini: 28.1 (#317), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| SciCode | 10.8% | — |
| LMArena Coding | — | 1436 |
Reasoning Too close to call
Phi-4 Mini: 22.4 (#195), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1411 |
Math Not comparable
Phi-4 Mini: —, Step 3.5 Flash: 42.6 (#84)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |
Knowledge Step 3.5 Flash leads
Phi-4 Mini: 25.3 (#262), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1421 |
Multilingual Not comparable
Phi-4 Mini: —, Step 3.5 Flash: 50.5 (#119)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Phi-4 Mini: —, Step 3.5 Flash: 73.1 (#124)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Not comparable
Phi-4 Mini: —, Step 3.5 Flash: 42.8 (#117)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Phi-4 Mini: —, Step 3.5 Flash: 58.8 (#113)
| Benchmark | Phi-4 Mini | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Phi-4 Mini better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.9 on the Noometry Index.
Which is cheaper, Phi-4 Mini or Step 3.5 Flash?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.
Is Phi-4 Mini or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 128K.
How many benchmarks do Phi-4 Mini and Step 3.5 Flash share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Step 3.5 Flash has 19.