GPT-4o (2024-05-13)
May 2024
GPT-4o (2024-05-13)Compare inon
Benchmarks of GPT-4o (2024-05-13)4
BenchmarkByScoreRank
Overall1
Science1
Legacy · saturated or no longer reported2
No benchmark matches
Ranking?
Strong at
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperClaude Sonnet 5.5max×7.6-47%$5.46No forced tool use+5BetterGPT-6 Lunalow×2.9-97%$0.005Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking×6.3-93%$0.13Pass back reasoning_content+3
CheaperGemini 4 Argonhigh×7.2-47%*$1.99Synchronous output stops at 65,536+2CheaperGPT-6.1 Solmax×7.1-47%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Claude Sonnet 5.5max×7.6-47%$5.46No forced tool use+5Gemini 4 Argonhigh×7.2-47%*$1.99Synchronous output stops at 65,536+2GPT-6.1 Solmax×7.1-47%$0.72Remove unsupported parameters+5
Muse Spark 1.3max×6.6-73%$1.60Only auto tool_choice is supported+5GPT-6 Solmax×6.5-47%$1.04ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.9-97%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.9-94%$0.01
Mistral Small 4thinkingOpen+54%-97%$0.015MiMo v2.5thinkingOpen×3-98%$0.019
DeepSeek V3 0324non-thinkingOpen+33%-95%$0.021No image inputModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×6.3-93%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×6.2-93%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×6.1-71%$2.01No image input+4
Step 5 PreviewthinkingOpen×6-81%$1.03No web search+3
Kimi K3maxOpen×5.9-20%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astramedium×6.8—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium×6.5—$0.21Remove unsupported parameters+5GPT-6 Solmedium×5.4—$0.25GPT-5.6 Solmedium×5.4—$0.50GPT-5.5medium×4.6—$0.90Prompts with >272K input tokensGPT-5.3 Codexxhigh×4.4—$1.75 / $14DeprecatedGPT-5.6 Terramedium×4.1—$0.18Prompts with >272K input tokensGPT-6 Lunamedium×4.1—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam1.8#337
AA Intelligence Index 4.3.2≈7.3#269
GPQA Diamond52.6#252
Coding
LiveCodeBench · AA archived33.4#113
FAQ
How much does GPT-4o (2024-05-13) cost?›
$5 per 1M input tokens and $15 per 1M output tokens.
Is GPT-4o (2024-05-13) free to use?›
There is no free API; the cheapest paid price is $5 per 1M input tokens.
How good is GPT-4o (2024-05-13), and what is it best at?›
#334 of 334 in Chat & Knowledge, #112 of 152 in Coding.
Is GPT-4o (2024-05-13) better than Qwen3 32B?›
On AA Intelligence Index 4.3.2, GPT-4o (2024-05-13) scores 7.3 vs 7.3 — about the same.
How can I use GPT-4o (2024-05-13)?›
Through the API of Azure, OpenAI.
What is the context window of GPT-4o (2024-05-13)?›
128K tokens, with up to 4K output tokens.
When was GPT-4o (2024-05-13) released? Is there a newer version?›
Released 2024-05-13. It is deprecated by the lab.
Is GPT-4o (2024-05-13) open source?›
No, GPT-4o (2024-05-13) is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-4o (2024-05-13) read images?›
It accepts text and images, PDF files as input.
What is GPT-4o (2024-05-13)?›
GPT-4o (2024-05-13) is a closed language model from OpenAI, released May 2024.
What are the best alternatives to GPT-4o (2024-05-13)?›
Claude Sonnet 5.5 (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).