Sponsored byFusecodeEnterprise coding API for Claude Code, Codex, and model workflows.

OpenAI

GPT-4o (2024-08-06) API Benchmarks, Pricing & Provider Data

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducin...

Category Performance

Scores across benchmark categories on a 0-100 scale.

Coverage: 3 / 8
Avg. score: 35.2

#1Math

45.6

#2Coding

32.4

#3Reasoning

27.5

No data:AgentsKnowledgeMultilingualMultimodalInstruction following

Specifications

Input and output token limits for this model, plus how it ranks on long-context understanding.

INPUT

128Ktokens

≈ 153.6 pages of text

OUTPUT

16.4Ktokens

8K128K1M4M

128K

Features

Technical Details

Input

Rankings

Excels at

Detailed scores

Updated: Jul 9, 2026

Speed & latency

2 metrics

Output speed111.4 tok/s#44 / 113Time to first token0.62 s#19 / 113

Output speed

Source: Artificial Analysis / GPT-4o (Aug '24)LMSpeed rank: #44 / 113Updated: Jul 9, 2026Confidence: 4

40122.0 tok/s

41113.2 tok/s

42112.6 tok/s

43111.7 tok/s

44GPT-4o (2024-08-06)111.4 tok/s

45

Time to first token

Source: Artificial Analysis / GPT-4o (Aug '24)LMSpeed rank: #19 / 113Updated: Jul 9, 2026Confidence: 4

150.58 s

160.60 s

170.61 s

180.62 s

19

Pricing

2 metrics

Input price$2.50/M#114 / 138Output price$10.00/M#103 / 138

Input price

Source: Artificial Analysis / GPT-4o (Aug '24)LMSpeed rank: #114 / 138Updated: Jul 9, 2026Confidence: 4

107$2.00/M

Reasoning & knowledge

4 metrics

GPQA52.1%#130 / 152HLE2.9%#148 / 150

GPQA

Source: Artificial Analysis / GPT-4o (Aug '24)LMSpeed rank: #130 / 152Updated: Jul 9, 2026Confidence: 4

12654.3%

Coding & agents

2 metrics

LiveCodeBench31.7%#83 / 108SciCode33.1%#97 / 149

LiveCodeBench

Source: Artificial Analysis / GPT-4o (Aug '24)LMSpeed rank: #83 / 108Updated: Jul 9, 2026Confidence: 4

7934.7%

Related model comparisons

GGPT-4o (2024-08-06) vs GPT-5.4

3 verified comparison points

Indexable

GGPT-4o (2024-08-06) vs GPT-5

3 verified comparison points

Indexable

CClaude Opus 4.6 vs GPT-4o (2024-08-06)

3 verified comparison points

Indexable

Data as of Jul 9, 2026, 08:20 AMRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Artificial AnalysisStandard benchmark data may include BenchLM and other public sources.

Output

Knowledge cutoff

2023-10-31

Documentation

Tokenizer

GPT

Architecture

text+image+file->text

Moderated

No

Supported parameters

frequency_penaltylogit_biaslogprobsmax_completion_tokensmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_pweb_search_options

Llama 4 Scout

109.6 tok/s

46DeepSeek V4 Flash107.9 tok/s

47GPT-5.4106.7 tok/s

48Qwen3 Coder 30B A3B Instruct105.1 tok/s

49GLM-4.7103.8 tok/s

GPT-4o (2024-08-06)

0.62 s

20GPT-4.1 Mini0.63 s

21Mistral Large 30.64 s

22Llama 4 Scout0.64 s

23GPT-4o Mini0.68 s