DataLearner logo

Llama3.1-8B-Instruct Benchmark Details

Llama3.1-8B-Instruct currently shows benchmark results led by GSM8K (16 / 26, score 82.40), MBPP (18 / 28, score 69.40), HumanEval (28 / 39, score 66.50).

Benchmark Results

Llama3.1-8B-Instruct

Benchmark Results

Thinking

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU
68.10
60 / 66
MMLU Pro
44
126 / 132
GPQA Diamond
26.30
180 / 187

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
82.40
16 / 26
MATH
47.60
35 / 42

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
69.40
18 / 28
HumanEval
66.50
28 / 39
Compare with other models