Updated daily at 05:00 UTC
- Released
- 20 Aug 2024
- Status
- Legacy
- Context
- 131.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- mit
- Parameters
- 3.82B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| MMLU-Pro | Accuracy | 47.9% | Self-reported | — | — | EvalEval via Hugging Face Community Evals |
| PIQA | Accuracy | 81.0% | Self-reported | — | — | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GSM8K | Exact match | 86.2% | Self-reported | — | — | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI |
Other Phi versions
- Phi-mini-MoE23 Jun 2025
- Phi-tiny-MoE23 Jun 2025
- Phi-4-mini26 Feb 2025
- Phi-412 Dec 2024
- Phi-3.5-MoE20 Aug 2024
- Phi-3-medium21 May 2024
- Phi-3-small21 May 2024
- Phi-3-mini23 Apr 2024
- Phi-212 Dec 2023
- Phi-1.511 Sep 2023
- Phi-110 Sep 2023