DataLearner logo

Qwen3-235B-A22B Benchmark Details

Qwen3-235B-A22B currently shows benchmark results led by GSM8K (2 / 26, score 96.40), MATH-500 (7 / 44, score 98), AIME 2024 (20 / 62, score 85.70).

Benchmark Results

Qwen3-235B-A22B

Benchmark Results

Thinking

General Knowledge

7 evaluations
Benchmark / mode
Score
Rank/total
BBH
88.87
8 / 20
MMLU
85.80
36 / 65
MMLU Pro
72.90
85 / 126
GPQA Diamond
71.10
109 / 179
GPQA Diamond
71.10
109 / 179
HLE
7.60
144 / 159
ARC-AGI
4.30
64 / 65

Math and Reasoning

7 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
98
7 / 44
MATH-500
96.20
19 / 44
GSM8K
96.40
2 / 26
AIME 2024
85.70
20 / 62
AIME 2024
85.70
20 / 62
AIME2025
81.50
54 / 106
AIME2025
24.70
102 / 106

阅读理解

1 evaluations
Benchmark / mode
Score
Rank/total
DROP
88.70
5 / 9

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
11
38 / 45

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
70.70
49 / 120
LiveCodeBench
70.70
49 / 120
SWE-bench Verified
34.40
101 / 108

Writing and Creative Capabilities

2 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
84.60
11 / 23
Creative Writing
80.40
18 / 23

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
31
21 / 27

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
34.40
39 / 40
Compare with other models