MicrosoftAuto-detectedPhi 3
Phi 3 is a Microsoft proprietary model. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories. Last measured 2 Sept 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Reasoning35
- Coding34
- Human preference34
Versions
Microsoft has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | medium | Source |
|---|---|---|
| LMArena Hard Prompts | 1212#300 | LMArena |
Coding
| Benchmark | medium | Source |
|---|---|---|
| LMArena Coding | 1231#303 | LMArena |
Human preference
| Benchmark | medium | Source |
|---|---|---|
| LMArena Text | 1197#299 | LMArena |
See also
Data as of 10 Sept 2026. Compare with another model.