DataLearner logo

Phi-4-mini-instruct (3.8B) Benchmark Details

Phi-4-mini-instruct (3.8B) currently shows benchmark results led by GSM8K (14 / 26, score 88.60), HumanEval (24 / 39, score 74.40), MATH (27 / 42, score 64).

Benchmark Results

Phi-4-mini-instruct (3.8B)

Benchmark Results

Thinking

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU
67.30
61 / 65
MMLU Pro
52.80
113 / 126
GPQA Diamond
36
168 / 179

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
88.60
14 / 26
MATH-500
71.80
44 / 44
MATH
64
27 / 42
AIME 2024
10
60 / 62

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
74.40
24 / 39
MBPP
65.30
20 / 28
Compare with other models