Benchmark
PhiBench
PhiBench is an internal benchmark designed to evaluate diverse skills and reasoning abilities of language models, covering a wide range of tasks including…
- Modality
- text
- Categories
- math, reasoning, general
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 3
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Phi 4 | Microsoft | 0.562 | 2024-12-12 | evidence |
| Phi 4 Reasoning | Microsoft | 0.706 | 2025-04-30 | evidence |
| Phi 4 Reasoning Plus | Microsoft | 0.742 | 2025-04-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.