math 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 coding (debugging, extending incomplete code, explaining code snippets) and mathematics (identifying proof errors, generating related problems). Created by Microsoft's research team to address limitations of standard academic benchmarks and guide the development of the Phi-4 model.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
PhiBench Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 74.2% | 100.0% | 3 | C | |
| 02 | MI | 70.6% | 50.0% | 3 | C | |
| 03 | MI | 56.2% | 0.0% | 3 | C |
PhiBench Score Distribution
A closer view of the leading scores on this benchmark.
PhiBench Highlights
The leading models and scores on this benchmark.
What is PhiBench?
What PhiBench measures and how its scores work.
PhiBench is an internal benchmark designed to evaluate diverse skills and reasoning abilities of language models, covering a wide range of tasks including coding (debugging, extending incomplete code, explaining code snippets) and mathematics (identifying proof errors, generating related problems). Created by Microsoft's research team to address limitations of standard academic benchmarks and guide the development of the Phi-4 model.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PhiBench
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- phibench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PhiBench.
Which model scores highest on PhiBench?
Phi 4 Reasoning Plus is currently ranked first with 74.2%.
What does PhiBench measure?
PhiBench is an internal benchmark designed to evaluate diverse skills and reasoning abilities of language models, covering a wide range of tasks including coding (debugging, extending incomplete code, explaining code snippets) and mathematics (identifying proof errors, generating related problems). Created by Microsoft's research team to address limitations of standard academic benchmarks and guide the development of the Phi-4 model.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.