Author's Description
Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Microsoft's Phi-3 Mini 128K Instruct, released on May 25, 2024, demonstrates exceptional performance in several key areas. It consistently ranks among the fastest models and offers highly competitive pricing across all benchmarks. With a 98% success rate, its reliability is outstanding, indicating minimal technical failures and consistent response generation. In terms of specific performance, Phi-3 Mini shows strong capabilities in Ethics (98.0% accuracy) and General Knowledge (93.4% accuracy), performing well within the 44th and 37th percentiles respectively. Its Coding accuracy of 59.0% is also respectable for a lightweight model. However, the model exhibits significant weaknesses in Instruction Following, achieving 0.0% accuracy, and Reasoning, with only 28.0% accuracy. Email Classification also presents a challenge, with an accuracy of 87.0% placing it in the 11th percentile. Despite these areas for improvement, its high reliability, speed, and cost-effectiveness make it a compelling option for tasks where its strengths align. The model is static, trained on data up to October 2023.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.1 |
Completion | $0.1 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Azure
|
Azure | microsoft/phi-3-mini-128k-instruct | 128K | $0.1 / 1M tokens | $0.1 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by microsoft
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Microsoft: Phi 4 Reasoning Plus | May 01, 2025 | ~14B | 32K |
Text input
Text output
|
★ | ★★★ | $$$$ |
Microsoft: MAI DS R1 | Apr 20, 2025 | — | 163K |
Text input
Text output
|
★★★★ | ★★★★★ | $$$ |
Microsoft: Phi 4 Multimodal Instruct | Mar 07, 2025 | ~5.6B | 131K |
Text input
Image input
Text output
|
★★ | ★★ | $$ |
Microsoft: Phi 4 | Jan 09, 2025 | ~14B | 16K |
Text input
Text output
|
★★★★ | ★★★★ | $$ |
Microsoft: Phi-3.5 Mini 128K Instruct | Aug 20, 2024 | ~3.8B | 128K |
Text input
Text output
|
★ | ★★ | $$ |
Microsoft: Phi-3 Medium 128K Instruct | May 23, 2024 | ~14B | 128K |
Text input
Text output
|
★★ | ★ | $$$$ |
WizardLM-2 8x22B | Apr 15, 2024 | 22B | 65K |
Text input
Text output
|
★★★ | ★★ | $$$ |