Moonshot v1 Benchmark Scores & Performance

Benchmark analysis of Moonshot v1 by Moonshot AI across 14 tests.

Creator

Moonshot AI

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

128K

Overall Score

44#64 of 88

Knowledge Benchmarks

MMLU
53
GPQA
52
SuperGPQA
50
OpenBookQA
48

Coding Benchmarks

HumanEval
45

Mathematics Benchmarks

AIME 2023
53
AIME 2024
55
AIME 2025
54
HMMT Feb 2023
49
HMMT Feb 2024
51
HMMT Feb 2025
50
BRUMO 2025
52

Reasoning Benchmarks

SimpleQA
51
MuSR
49

Frequently Asked Questions

How does Moonshot v1 perform overall in AI benchmarks?

Moonshot v1 ranks #64 out of 88 models with an overall score of 44. It is created by Moonshot AI and features a 128K context window.

Is Moonshot v1 good for knowledge and understanding?

Moonshot v1 ranks #64 out of 88 models in knowledge and understanding benchmarks with an average score of 50.8. There are stronger options in this category.

Is Moonshot v1 good for coding and programming?

Moonshot v1 ranks #64 out of 88 models in coding and programming benchmarks with an average score of 45. There are stronger options in this category.

Is Moonshot v1 good for mathematics?

Moonshot v1 ranks #64 out of 88 models in mathematics benchmarks with an average score of 52. There are stronger options in this category.

Is Moonshot v1 good for reasoning and logic?

Moonshot v1 ranks #64 out of 88 models in reasoning and logic benchmarks with an average score of 50. There are stronger options in this category.

What is the context window size of Moonshot v1?

Moonshot v1 has a context window of 128K tokens, which determines how much text it can process in a single interaction.