Skip to main content

GPT-4o

OpenAISupersededReleased May 13, 2024
Overall Score
Est. 42Prov. #77 of 119
Arena Elo
1335
Categories Ranked
8of 8
Price (1M tokens)
$2.5 in / $10 out
Speed
131tok/s
Context
128K
ProprietaryNon-Reasoning
Confidence
base

According to BenchLM.ai, GPT-4o ranks #77 out of 119 models on the provisional leaderboard with an overall score of 42/100. 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.

GPT-4o 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.

GPT-4o sits inside the GPT-4o family alongside GPT-4o mini. This profile currently has 16 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 (#47), while its weakest is Instruction Following (#75). 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

#61
39.9/ 100
Weight: 22%4 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#72
25.4/ 100
Weight: 20%3 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#57
46.4/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#75
35.6/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#49
52.0/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#58
50.1/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#47
61.5/ 100
Weight: 12%0 benchmarks
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#75
54.9/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1335

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.

GPT-4o Family

Base entry

Frequently Asked Questions

How does GPT-4o perform overall in AI benchmarks?

GPT-4o currently ranks #77 out of 119 models on BenchLM's provisional leaderboard with an overall score of 42 (estimated). It is created by OpenAI and features a 128K context window.

Is GPT-4o good for knowledge and understanding?

GPT-4o ranks #75 out of 119 models in knowledge and understanding benchmarks with an average score of 35.6. There are stronger options in this category.

Is GPT-4o good for coding and programming?

GPT-4o ranks #72 out of 119 models in coding and programming benchmarks with an average score of 25.4. There are stronger options in this category.

Is GPT-4o good for reasoning and logic?

GPT-4o ranks #57 out of 119 models in reasoning and logic benchmarks with an average score of 46.4. There are stronger options in this category.

Is GPT-4o good for agentic tool use and computer tasks?

GPT-4o ranks #61 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 39.9. There are stronger options in this category.

Is GPT-4o good for instruction following?

GPT-4o ranks #75 out of 119 models in instruction following benchmarks with an average score of 54.9. There are stronger options in this category.

Which sibling models are related to GPT-4o?

GPT-4o belongs to the GPT-4o family. Related variants on BenchLM include GPT-4o mini.

Does GPT-4o have full benchmark coverage on BenchLM?

Not yet. GPT-4o currently has 16 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 GPT-4o?

GPT-4o 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.