Hunyuan-A13B-Instruct Benchmark Details

Hunyuan-A13B-Instruct currently shows benchmark results led by MATH (3 / 42, score 94.30), AIME 2024 (17 / 62, score 87.30), MMLU (20 / 65, score 88.17).

Benchmark Results

Hunyuan-A13B-Instruct

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

BBH

Standard Mode

89.10

7 / 20

MMLU

Standard Mode

88.17

20 / 65

GPQA Diamond

Standard Mode

71.20

103 / 175

MMLU Pro

Standard Mode

67.23

95 / 124

GPQA

Standard Mode

49.12

7 / 14

数学推理

4 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

94.30

3 / 42

GSM8K

Standard Mode

91.83

10 / 26

AIME 2024

Standard Mode

87.30

17 / 62

AIME2025

Standard Mode

76.80

64 / 106

编程与软件工程

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

83.86

9 / 28

LiveCodeBench

Standard Mode

63.90

63 / 118

Compare with other models