DataLearner logo

Qwen3-32B Benchmark Details

Qwen3-32B currently shows benchmark results led by C-Eval (9 / 48, score 87.30), MATH-500 (14 / 45, score 97.20), AIME 2024 (25 / 62, score 81.40).

Benchmark Results

Qwen3-32B

Benchmark Results

Thinking

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Standard Mode
83.30
11 / 48
C-Eval
Thinking Enabled
87.30
9 / 48
LiveBench
Thinking Enabled
43.56
107 / 117

Other

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
54.60
240 / 274
GPQA Diamond
Thinking Enabled
68.40
205 / 274

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
88.60
39 / 45
MATH-500
Thinking Enabled
97.20
14 / 45
AIME 2024
Standard Mode
31
55 / 62
AIME 2024
Thinking Enabled
81.40
25 / 62
AIME2025
Standard Mode
20.20
106 / 107
AIME2025
Thinking Enabled
72.90
70 / 107

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
CodeForces
Standard Mode
1353
19 / 21
CodeForces
Thinking Enabled
1977
16 / 21
LiveCodeBench
Standard Mode
31.30
122 / 128
LiveCodeBench
Thinking Enabled
65.70
66 / 128

Agent Level Benchmark

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