Model comparison
Phi-2 vs Step 1o Turbo 202506
Step 1o Turbo 202506 has enough public results to be ranked (#160); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
StepFunSummary
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Phi-2 | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | — | 39.1 |
| Released | 2023-12-12 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-2: —, Step 1o Turbo 202506: 38.6 (#158)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | — | 1339 |
| HumanEval+ | 45.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Not comparable
Phi-2: —, Step 1o Turbo 202506: 25.7 (#127)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | — | 1336 |
| Adversarial NLI | 42.5% | — |
| BIG-Bench Hard | 59.4% | — |
| Epoch Capabilities Index | 107.62 | — |
| HellaSwag | 53.6% | — |
| WinoGrande | 54.7% | — |
Math Not comparable
Phi-2: —, Step 1o Turbo 202506: 33.9 (#163)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | — | 1318 |
Knowledge Not comparable
Phi-2: —, Step 1o Turbo 202506: 35.5 (#174)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | — | 1308 |
| ARC (AI2) Challenge | 75.9% | — |
| MMLU | 58.4% | — |
| OpenBookQA | 73.6% | — |
| TriviaQA | 45.2% | — |
Multimodal Not comparable
Phi-2: —, Step 1o Turbo 202506: 35.4 (#75)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Not comparable
Phi-2: —, Step 1o Turbo 202506: 45.5 (#168)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1380 |
| LMArena German | — | 1315 |
| LMArena Russian | — | 1327 |
Instruction Following Not comparable
Phi-2: —, Step 1o Turbo 202506: 69.4 (#171)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | — | 1311 |
Long Context Not comparable
Phi-2: —, Step 1o Turbo 202506: 41.1 (#141)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | — | 1350 |
Writing & Preference Not comparable
Phi-2: —, Step 1o Turbo 202506: 53.4 (#154)
| Benchmark | Phi-2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | — | 1336 |
| LMArena Creative Writing | — | 1308 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Phi-2 better than Step 1o Turbo 202506?
Step 1o Turbo 202506 has enough public results to be ranked (#160); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Phi-2 and Step 1o Turbo 202506 share?
0 benchmarks have published results for both models. Phi-2 has 11 scored results on Noometry and Step 1o Turbo 202506 has 14.