Model Comparison

Comprehensive side-by-side analysis of model capabilities and performance

Microsoft

Phi 4

Microsoft

Phi 4 is a language model developed by Microsoft. It achieves strong performance with an average score of 66.0% across 13 benchmarks. It excels particularly in MMLU (84.8%), HumanEval+ (82.8%), HumanEval (82.6%). The model shows particular specialization in math tasks with an average performance of 80.5%. The model is available through 1 API provider. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Microsoft's latest advancement in AI technology.

Microsoft

Phi 4 Mini Reasoning

Microsoft

Phi 4 Mini Reasoning is a language model developed by Microsoft. It achieves strong performance with an average score of 68.0% across 3 benchmarks. It excels particularly in MATH-500 (94.6%), AIME (57.5%), GPQA (52.0%). It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents Microsoft's latest advancement in AI technology.

Microsoft

Phi 4

Microsoft

2024-12-12

Microsoft

Phi 4 Mini Reasoning

Microsoft

2025-04-30

4 months newer

Performance Metrics

Context window and performance specifications

Microsoft

Phi 4

Larger context
Max Context:32.0K
Parameters:14.7B
Microsoft

Phi 4 Mini Reasoning

Max Context:-
Parameters:3.8B

Average performance across 1 common benchmarks

Microsoft

Phi 4

+4.1%
Average Score:56.1%
Microsoft

Phi 4 Mini Reasoning

Average Score:52.0%

Performance comparison across key benchmark categories

Microsoft

Phi 4

math
80.5%
general
+5.5%
60.2%
Microsoft

Phi 4 Mini Reasoning

math
+14.1%
94.6%
general
54.8%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores
Knowledge Cutoff
Training data recency comparison

Phi 4

2024-06-01

Phi 4 Mini Reasoning

2025-02-01

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Microsoft

Phi 4

1 providers

DeepInfra

Throughput: 33 tok/s
Latency: 0.2ms
Microsoft

Phi 4 Mini Reasoning

0 providers
Microsoft

Phi 4

+4.1%
Avg Score:56.1%
Providers:1
Microsoft

Phi 4 Mini Reasoning

Avg Score:52.0%
Providers:0