Model comparison
Phi 3 Mini 4k Instruct vs Step 1o Turbo 202506
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Microsoft
StepFunSummary
- They share 13 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Step 1o Turbo 202506 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 1o Turbo 202506 leads 53.1 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 1o Turbo 202506 | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 27.9 | 39.7 |
| Released | 2024-04-23 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1093 | 1339 |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1335 |
| 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 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1111 | 1318 |
| LiveBench Math | 15.7% | — |
Knowledge Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1045 | 1308 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multimodal Not comparable
Phi 3 Mini 4k Instruct: —, Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1021 | 1313 |
| LMArena Chinese | 1021 | 1380 |
| LMArena German | 1044 | 1314 |
| LMArena Russian | 1022 | 1327 |
| LMArena French | 1076 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Spanish | 1085 | — |
Instruction Following Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1053 | 1310 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1044 | 1348 |
Writing & Preference Step 1o Turbo 202506 leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Phi 3 Mini 4k Instruct | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1073 | 1336 |
| LMArena Creative Writing | 1037 | 1307 |
| LMArena Multi-Turn | 1018 | 1340 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Step 1o Turbo 202506?
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Step 1o Turbo 202506 share?
13 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Step 1o Turbo 202506 has 14.