DataLearner logo

Llama-3.2-3B Benchmark Details

Llama-3.2-3B currently shows benchmark results led by MBPP (71 / 96, score 48.70), GSM8K (53 / 70, score 34), MMLU (101 / 124, score 54.75).

Benchmark Results

Llama-3.2-3B

Benchmark Results

Thinking

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
54.75
101 / 124
BBH
Standard Mode
46.80
19 / 21
MMLU Pro
Standard Mode
25
169 / 176
MMLU Pro
unknown
22.17
171 / 176

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
34
53 / 70
MATH
Standard Mode
8.50
42 / 42

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
48.70
71 / 96
HumanEval
Standard Mode
28
123 / 140

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
26.60
451 / 462

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
593.50
105 / 106
Compare with other models