Updated daily at 05:00 UTC
- Released
- 12 Dec 2024
- Status
- Current
- Context
- 16.4K
- Max output
- —
- Input per 1M tokens
- $0.13
- Output per 1M tokens
- $0.50
- Open weights
- Yes
- License
- mit
- Parameters
- 14.66B
- 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.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 0.0 | Not ranked | 1 of 4 |
| Agentic tool use | 11.6 | Not ranked | 1 of 2 |
| Human preference | 30.4 | Not ranked | 1 of 5 |
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 |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 1.0% | Independent | — | 28 Aug 2026 | Epoch AI |
| MMLU | Accuracy | 84.8% | Self-reported | — | — | Phi-4 Technical Report via Epoch AI |
| MMLU-Pro | Accuracy | 70.4% | Self-reported | — | — | EvalEval via Hugging Face Community Evals |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 56.1% | Independent | — | 31 Jan 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| MATH Level 5 | Accuracy | 64.9% | Independent | — | 31 Jan 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 13.8% | Independent | — | 25 Feb 2025 | Epoch AI |
Agentic tool use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| BALROG | Average progress | 11.6% | Third party | — | — | https://balrogai.com/ via Epoch AI |
Writing
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 62.6% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1256 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 24126 | Independent | — | 25 Sep 2026 | Arena |
Other Phi versions
- Phi-mini-MoE23 Jun 2025
- Phi-tiny-MoE23 Jun 2025
- Phi-4-mini26 Feb 2025
- Phi-3.5-mini20 Aug 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