DataLearner logo

ERNIE-4.5-300B-A47B Benchmark Details

ERNIE-4.5-300B-A47B currently shows benchmark results led by GSM8K (1 / 70, score 96.60), BBH (1 / 21, score 94.30), DROP (2 / 9, score 91.10).

Benchmark Results

ERNIE-4.5-300B-A47B

Benchmark Results

Thinking
Tool usage

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
BBH
Standard Mode
94.30
1 / 21
MMLU
Standard Mode
86.50
29 / 124
MMLU Pro
Standard Mode
78.40
72 / 176
HLE
Standard Mode
3.30
552 / 563

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
96.60
1 / 70
MATH-500
Standard Mode
96.40
17 / 45
AIME 2024
Standard Mode
54.80
44 / 62
AIME2025
Standard Mode
35.10
177 / 215

Reading Comprehension

1 evaluations
Benchmark / mode
Score
Rank/total
DROP
Standard Mode
91.10
2 / 9

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
81.10
216 / 462

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
45.90
15 / 47

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
38.80
189 / 250

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Standard Mode
39.10
222 / 282

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench Hard
Standard ModeTools
6.10
204 / 244