Baichuan2-13B-Base Benchmark Details

Baichuan2-13B-Base currently shows benchmark results led by AGIEval (9 / 28, score 48.17), C-Eval (25 / 48, score 58.10), GSM8K (43 / 70, score 52.77).

Benchmark Results

Baichuan2-13B-Base

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

59.17

94 / 124

C-Eval

Standard Mode

58.10

25 / 48

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

52.77

43 / 70

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

30.20

62 / 70

HumanEval

Standard Mode

17.07

96 / 101

Other

1 evaluations

Benchmark / mode

Score

Rank/total

AGIEval

Standard Mode

48.17

9 / 28

Compare with other models