Skip to main content

Grok 4

xAIEstablishedReleased Jul 9, 2025
Overall Score
Est. 63Prov. #47 of 119
Arena Elo
1410
Categories Ranked
8of 8
Price (1M tokens)
$ in / $ out
Speed
54tok/s
Context
128K
ProprietaryNon-Reasoning
Confidence
base

According to BenchLM.ai, Grok 4 ranks #47 out of 119 models on the provisional leaderboard with an overall score of 63/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Grok 4 is a proprietary model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 19 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#24), while its weakest is Instruction Following (#73). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#43
54.1/ 100
Weight: 22%5 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#27
76.9/ 100
Weight: 20%4 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#45
55.1/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#43
65.3/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#24
80.0/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#42
65.4/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#24
72.2/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#73
54.9/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1410

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does Grok 4 perform overall in AI benchmarks?

Grok 4 currently ranks #47 out of 119 models on BenchLM's provisional leaderboard with an overall score of 63 (estimated). It is created by xAI and features a 128K context window.

Is Grok 4 good for knowledge and understanding?

Grok 4 ranks #43 out of 119 models in knowledge and understanding benchmarks with an average score of 65.3. There are stronger options in this category.

Is Grok 4 good for coding and programming?

Grok 4 ranks #27 out of 119 models in coding and programming benchmarks with an average score of 76.9. There are stronger options in this category.

Is Grok 4 good for reasoning and logic?

Grok 4 ranks #45 out of 119 models in reasoning and logic benchmarks with an average score of 55.1. There are stronger options in this category.

Is Grok 4 good for agentic tool use and computer tasks?

Grok 4 ranks #43 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 54.1. There are stronger options in this category.

Is Grok 4 good for multimodal and grounded tasks?

Grok 4 ranks #24 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 72.2. There are stronger options in this category.

Is Grok 4 good for instruction following?

Grok 4 ranks #73 out of 119 models in instruction following benchmarks with an average score of 54.9. There are stronger options in this category.

Does Grok 4 have full benchmark coverage on BenchLM?

Not yet. Grok 4 currently has 19 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Grok 4?

Grok 4 has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.