DataLearner logo

Qwen3-32B Benchmark Details

Qwen3-32B currently shows benchmark results led by MATH-500 (14 / 44, score 97.20), AIME 2024 (25 / 62, score 81.40), LiveCodeBench (61 / 120, score 65.70).

Benchmark Results

Qwen3-32B

Benchmark Results

Thinking

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Standard Mode
83.30
9 / 9
C-Eval
Thinking Enabled
87.30
8 / 9
GPQA Diamond
Standard Mode
54.60
152 / 182
GPQA Diamond
Thinking Enabled
68.40
123 / 182
LiveBench
Thinking Enabled
43.56
105 / 115

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
88.60
38 / 44
MATH-500
Thinking Enabled
97.20
14 / 44
AIME 2024
Standard Mode
31
55 / 62
AIME 2024
Thinking Enabled
81.40
25 / 62
AIME2025
Standard Mode
20.20
105 / 106
AIME2025
Thinking Enabled
72.90
69 / 106

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
CodeForces
Standard Mode
1353
16 / 16
CodeForces
Thinking Enabled
1977
14 / 16
LiveCodeBench
Standard Mode
31.30
114 / 120
LiveCodeBench
Thinking Enabled
65.70
61 / 120

Writing and Creative Capabilities

2 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
78.30
19 / 23
Creative Writing
Thinking Enabled
81
17 / 23

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
40
39 / 59
Compare with other models