Kimi K2 Benchmark Scores & Performance

Benchmark analysis of Kimi K2 by Moonshot AI across 14 tests.

Creator

Moonshot AI

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

128K

Overall Score

23#85 of 88

Knowledge Benchmarks

MMLU
32
GPQA
31
SuperGPQA
29
OpenBookQA
27

Coding Benchmarks

HumanEval
24

Mathematics Benchmarks

AIME 2023
32
AIME 2024
34
AIME 2025
33
HMMT Feb 2023
28
HMMT Feb 2024
30
HMMT Feb 2025
29
BRUMO 2025
31

Reasoning Benchmarks

SimpleQA
30
MuSR
28

Frequently Asked Questions

How does Kimi K2 perform overall in AI benchmarks?

Kimi K2 ranks #85 out of 88 models with an overall score of 23. It is created by Moonshot AI and features a 128K context window.

Is Kimi K2 good for knowledge and understanding?

Kimi K2 ranks #85 out of 88 models in knowledge and understanding benchmarks with an average score of 29.8. There are stronger options in this category.

Is Kimi K2 good for coding and programming?

Kimi K2 ranks #85 out of 88 models in coding and programming benchmarks with an average score of 24. There are stronger options in this category.

Is Kimi K2 good for mathematics?

Kimi K2 ranks #85 out of 88 models in mathematics benchmarks with an average score of 31. There are stronger options in this category.

Is Kimi K2 good for reasoning and logic?

Kimi K2 ranks #85 out of 88 models in reasoning and logic benchmarks with an average score of 29. There are stronger options in this category.

What is the context window size of Kimi K2?

Kimi K2 has a context window of 128K tokens, which determines how much text it can process in a single interaction.