Qwen3.5 397B (Reasoning) Benchmark Scores & Performance

Benchmark analysis of Qwen3.5 397B (Reasoning) by Alibaba across 14 tests.

Creator

Alibaba

Source Type

Open Weight

Reasoning

Reasoning

Context Window

128K

Overall Score

70#21 of 88

Knowledge Benchmarks

MMLU
91
GPQA
89
SuperGPQA
87
OpenBookQA
85

Coding Benchmarks

HumanEval
83

Mathematics Benchmarks

AIME 2023
93
AIME 2024
95
AIME 2025
94
HMMT Feb 2023
89
HMMT Feb 2024
91
HMMT Feb 2025
90
BRUMO 2025
92

Reasoning Benchmarks

SimpleQA
87
MuSR
85

Frequently Asked Questions

How does Qwen3.5 397B (Reasoning) perform overall in AI benchmarks?

Qwen3.5 397B (Reasoning) ranks #21 out of 88 models with an overall score of 70. It is created by Alibaba and features a 128K context window.

Is Qwen3.5 397B (Reasoning) good for knowledge and understanding?

Qwen3.5 397B (Reasoning) ranks #21 out of 88 models in knowledge and understanding benchmarks with an average score of 88. There are stronger options in this category.

Is Qwen3.5 397B (Reasoning) good for coding and programming?

Qwen3.5 397B (Reasoning) ranks #21 out of 88 models in coding and programming benchmarks with an average score of 83. There are stronger options in this category.

Is Qwen3.5 397B (Reasoning) good for mathematics?

Qwen3.5 397B (Reasoning) ranks #21 out of 88 models in mathematics benchmarks with an average score of 92. There are stronger options in this category.

Is Qwen3.5 397B (Reasoning) good for reasoning and logic?

Qwen3.5 397B (Reasoning) ranks #21 out of 88 models in reasoning and logic benchmarks with an average score of 86. There are stronger options in this category.

Is Qwen3.5 397B (Reasoning) open source?

Yes, Qwen3.5 397B (Reasoning) is an open weight model created by Alibaba, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

What is the context window size of Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) has a context window of 128K tokens, which determines how much text it can process in a single interaction.