Model comparison
Phi 3 Mini 4k Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 27.9 | 47.9 |
| Released | 2024-04-23 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Step 5 Preview: 51.8 (#36)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1093 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Step 5 Preview leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Step 5 Preview: 40.0 (#57)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Step 5 Preview leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Step 5 Preview: 46.1 (#72)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1111 | 1470 |
| ProofBench | — | 42% |
| LiveBench Math | 15.7% | — |
Knowledge Step 5 Preview leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Step 5 Preview: 41.2 (#112)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1045 | 1470 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multimodal Not comparable
Phi 3 Mini 4k Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Step 5 Preview: 53.8 (#54)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1021 | 1432 |
| LMArena Chinese | 1021 | 1519 |
| LMArena Russian | 1022 | 1436 |
| LMArena Spanish | 1085 | 1439 |
| LMArena French | 1076 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
Instruction Following Step 5 Preview leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Step 5 Preview: 76.0 (#50)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1053 | 1444 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Step 5 Preview leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Step 5 Preview: 44.5 (#64)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1044 | 1455 |
Writing & Preference Step 5 Preview leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Step 5 Preview: 62.8 (#71)
| Benchmark | Phi 3 Mini 4k Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1073 | 1442 |
| LMArena Creative Writing | 1037 | 1410 |
| LMArena Multi-Turn | 1018 | 1447 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct 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.
How many benchmarks do Phi 3 Mini 4k Instruct and Step 5 Preview share?
13 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Step 5 Preview has 18.