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-3.5-MoE-instruct

Microsoft

Phi-3.5-MoE-instruct is a language model developed by Microsoft. It achieves strong performance with an average score of 65.6% across 31 benchmarks. It excels particularly in ARC-C (91.0%), OpenBookQA (89.6%), GSM8k (88.7%). The model shows particular specialization in reasoning tasks with an average performance of 85.4%. 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-3.5-MoE-instruct

Microsoft

2024-08-23

Microsoft

Phi 4

Microsoft

2024-12-12

3 months newer

Performance Metrics

Context window and performance specifications

Microsoft

Phi 4

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

Phi-3.5-MoE-instruct

Max Context:-
Parameters:60.0B

Average performance across 7 common benchmarks

Microsoft

Phi 4

+20.4%
Average Score:75.8%
Microsoft

Phi-3.5-MoE-instruct

Average Score:55.4%

Performance comparison across key benchmark categories

Microsoft

Phi 4

math
+11.5%
80.5%
code
+0.4%
76.1%
general
60.2%
Microsoft

Phi-3.5-MoE-instruct

math
69.0%
code
75.8%
general
+0.7%
60.9%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores
Knowledge Cutoff
Training data recency comparison

Phi 4

2024-06-01

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-3.5-MoE-instruct

0 providers
Microsoft

Phi 4

+20.4%
Avg Score:75.8%
Providers:1
Microsoft

Phi-3.5-MoE-instruct

Avg Score:55.4%
Providers:0