Microsoft·released 2024-12-11✓ 2 sources
Phi-4 benchmark scores: 7 benchmarks tracked. 43% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 79.73 on MMLU (self-reported)·3 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 79.73accuracy (%) | self-reported· optimizedT1 | 2024-12-12Phi-4 Technical Report |
| MATH level 5 | 64.94accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| Lech Mazur Writing | 62.6accuracy (%) | unverifiedT1 | 2024-12-12lechmazur/writing Github repository |
| GPQA diamond | 41.41accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| OTIS Mock AIME 2024-2025 | 13.66accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| Balrog | 11.6accuracy (%) | unverifiedT1 | 2024-12-12https://balrogai.com/ |
| Chess Puzzles | 0accuracy (%) | unverifiedT2 | 2024-12-12 |
Claims drawn from cited facts, not live model generation.
Developed by Microsoft and released in 2024, this model is a mid-size system at 14.66 billion parameters. That scale buys efficiency and lower deployment cost, at the price of less capacity headroom than the largest frontier-scale models command.
4 cited facts
This model is scored on 7 tracked benchmarks, and it currently holds no top score on any of them. Because its record has been independently reproduced, outside evaluation backs up those scores, so the reported results can be read as verified rather than merely claimed.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 47.21 points.
1 cited fact
6 facts cross-checked across data sources: 1 corroborated, 5 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, huggingface_models, openrouter_models
Phi-4 is an AI model developed by Microsoft, released 2024-12-11. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Phi-4 has recorded scores on 7 benchmarks, each shown with its evidence status.
Phi-4 has recorded scores on 7 benchmarks — Lech Mazur Writing, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, MMLU, Chess Puzzles, and 1 more. The full table above shows each score with its evidence status.
3 of 7 recorded scores (43%) are independently reproduced rather than self-reported by the lab.
Phi-4 has 7 tracked claims: 3 independently reproduced, 1 self-reported, 3 unverified.