Grok 3 [Beta] Benchmark Scores & Performance

Benchmark analysis of Grok 3 [Beta] by xAI across 14 tests.

Creator

xAI

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

128K

Overall Score

33#75 of 88

Knowledge Benchmarks

MMLU
42
GPQA
41
SuperGPQA
39
OpenBookQA
37

Coding Benchmarks

HumanEval
34

Mathematics Benchmarks

AIME 2023
42
AIME 2024
44
AIME 2025
43
HMMT Feb 2023
38
HMMT Feb 2024
40
HMMT Feb 2025
39
BRUMO 2025
41

Reasoning Benchmarks

SimpleQA
40
MuSR
38

Frequently Asked Questions

How does Grok 3 [Beta] perform overall in AI benchmarks?

Grok 3 [Beta] ranks #75 out of 88 models with an overall score of 33. It is created by xAI and features a 128K context window.

Is Grok 3 [Beta] good for knowledge and understanding?

Grok 3 [Beta] ranks #75 out of 88 models in knowledge and understanding benchmarks with an average score of 39.8. There are stronger options in this category.

Is Grok 3 [Beta] good for coding and programming?

Grok 3 [Beta] ranks #75 out of 88 models in coding and programming benchmarks with an average score of 34. There are stronger options in this category.

Is Grok 3 [Beta] good for mathematics?

Grok 3 [Beta] ranks #75 out of 88 models in mathematics benchmarks with an average score of 41. There are stronger options in this category.

Is Grok 3 [Beta] good for reasoning and logic?

Grok 3 [Beta] ranks #75 out of 88 models in reasoning and logic benchmarks with an average score of 39. There are stronger options in this category.

What is the context window size of Grok 3 [Beta]?

Grok 3 [Beta] has a context window of 128K tokens, which determines how much text it can process in a single interaction.