phi-3-mini 3.8B
ModelOpen sourceActiveby Microsoft · family “phi-minib”
Epoch Capabilities Index
117.2 #203 of 268
90% CI 106.4 – 120.8
Released
23 Apr 2024
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (9)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | games | 0.0% | 0% | — | 30 Aug 2026 | Eval log ↗ |
| BBH | reasoning | 71.7% | 80% | — | — | External ↗ |
| MMLU | knowledge | 68.8% | 78% | — | — | External ↗ |
| ANLI | other | 52.8% | 91% | — | — | External ↗ |
| Winogrande | other | 70.8% | 79% | — | — | External ↗ |
| HellaSwag | reasoning | 76.7% | 80% | — | — | External ↗ |
| OpenBookQA | other | 88.0% | 100% | — | — | External ↗ |
| ARC AI2 | other | 84.9% | 89% | — | — | External ↗ |
| TriviaQA | other | 64.0% | 73% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
This model has no public API price listing
0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 9h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates phi-3-mini 3.8BEpoch AI Benchmarking Hub