Qwen3.5-397B-A17B Benchmark Details

Qwen3.5-397B-A17B currently shows benchmark results led by MMLU Pro (8 / 115, score 87.80), IF Bench (2 / 27, score 76.50), Pinch Bench (3 / 37, score 89.10). 1 source link is attached for reference.

Benchmark Results

Qwen3.5-397B-A17B

Benchmark Results

综合评估

5 evaluations

Benchmark / mode

Score

Rank/total

C-Eval

3 / 5

GPQA Diamond

88.40

16 / 162

MMLU Pro

87.80

8 / 115

HLE

28.70

48 / 119

HLE

OnToolsInternet

48.30

13 / 119

编程与软件工程

4 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

83.60

12 / 108

SWE-bench Verified

OnTools

76.40

16 / 93

SWE-bench Multilingual

69.30

5 / 7

SWE-Bench Pro - Public

50.90

11 / 22

多模态理解

1 evaluations

Benchmark / mode

Score

Rank/total

MMMU

4 / 28

Agent能力评测

2 evaluations

Benchmark / mode

Score

Rank/total

Pinch Bench

OnTools

89.10

3 / 37

τ²-Bench

OnTools

86.70

7 / 39

指令跟随

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

76.50

2 / 27

AI Agent - 信息收集

2 evaluations

Benchmark / mode

Score

Rank/total

BrowseComp

OnToolsInternet

78.60

5 / 33

BrowseComp

OnTools

11 / 33

AI Agent - 工具使用

3 evaluations

Benchmark / mode

Score

Rank/total

OSWorld-Verified

OnTools

62.20

5 / 10

Terminal Bench 2.0

OnTools

52.50

13 / 28

Tool Decathlon

OnTools

38.30

3 / 4

数学推理

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

91.30

7 / 9

IMO-AnswerBench

80.90

7 / 7

长上下文能力

1 evaluations

Benchmark / mode

Score

Rank/total

AA-LCR

68.70

5 / 13

Compare with other models

Sources

qwen.ai