MicrosoftAuto-detectedphi-3-medium 14B
Best configuration ranks #548 of 610 on the BenchLeader Index at 38.5 ±3.8. Last measured 2 Sept 2026. Released 23 Apr 2024.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Overall index39
- Reasoning27
- Coding34
- Maths32
- Human preference34
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 | default | Source |
|---|---|---|
| GPQA Diamond | 27.6%#256 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1212#288 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1231#291 | LMArena |
Maths
| Benchmark | default | Source |
|---|---|---|
| MATH Level 5 | 17.6%#75 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1197#287 | LMArena |
See also
Data as of 9 Sept 2026. Compare with another model.