o3 (2025-04-16)
Apr 2025
o3 (2025-04-16)Compare inon
Benchmarks of o3 (2025-04-16)31
BenchmarkByScoreRank
Knowledge15
Reasoning1
Math4
Legacy · saturated or no longer reported11
No benchmark matches
Rankingat medium effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemini 3.8 Flashhigh×2-57%*$1.24Sampling parameters are ignored+1
BetterClaude Haiku 5.5max+30%-94%$0.21Remove sampling parameters+5
OpenDeepSeek V4 Pro 0813max+87%-43%$0.67No image input+5
CheaperGrok 4.6xhigh+48%-14%$1.75
CheaperGLM 5.3maxOpen+43%-39%$2.01No image input+4ModelScoreCostPer taskWhat changes
Gemini 3.8 Flashhigh×2-57%*$1.24Sampling parameters are ignored+1DeepSeek V4 Pro 0813maxOpen+87%-43%$0.67No image input+5Grok 4.6xhigh+48%-14%$1.75GLM 5.3maxOpen+43%-39%$2.01No image input+4
Qwen3.7 Maxmax+39%-37%$1.48 / $4.43No image inputModelScoreCostPer taskWhat changes
Claude Haiku 5.5max+30%-94%$0.21Remove sampling parameters+5GPT-5.6 Sollow+13%+129%$0.26DeepSeek V4 Pro 0813maxOpen+87%-43%$0.67No image input+5GPT-6.1 Solmax×3.5+14%$0.72Remove unsupported parameters+5GPT-6 Solmax×2.4+14%$1.04ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+87%-43%$0.67No image input+5GLM 5.3maxOpen+43%-39%$2.01No image input+4
Kimi K3maxOpen+13%+71%$2.00Sampling parameters are fixed+3Qwen3.6 35B A3BnoneOpen-4%-84%$0.25 / $1.49
Nemotron 3 UltraunstatedOpen-13%-71%$0.50 / $2.50No image inputModelScoreCostPer taskWhat changes
GPT-6 Astramax×3.7—$3.26Monitoring can return HTTP 403+2GPT-6.1 Solmax×3.5—$0.72Remove unsupported parameters+5GPT-5.6 Solmax×2.5—$1.99GPT-6 Solmax×2.4—$1.04GPT-5.5xhigh×2.4—$2.63Prompts with >272K input tokensGPT-5.4 (2026-03-05)medium+22%—$2.50 / $15GPT-5.2 (2025-12-11)medium-4%—$1.75 / $14GPT-5.1 (2025-11-13)medium-30%—$1.25 / $10All OpenAI models →Benchmarks
all categoriesChat & Knowledge
FrontierMath16.9#22
FrontierMath Tiers 1–3 (v2)29.8#57
Chess Puzzles37#31
Mystery Game Puzzles23#31
GPQA Diamond · Epoch80.8#67
OTIS Mock AIME 2024 202584.4#62
Coding
SWE-bench Verified · Epoch62.3#20
FAQ
How much does o3 (2025-04-16) cost?›
$2 per 1M input tokens and $8 per 1M output tokens.
Is o3 (2025-04-16) free to use?›
There is no free API; the cheapest paid price is $2 per 1M input tokens.
How good is o3 (2025-04-16), and what is it best at?›
#86 of 188 in Chat & Knowledge, #20 of 24 in Coding, #4 of 39 in Agents & Tool Use, #91 of 187 in Writing & Language.
Is o3 (2025-04-16) better than Grok 4.7?›
On Mystery Game Puzzles, o3 (2025-04-16) scores 29 vs 29 — about the same.
How can I use o3 (2025-04-16)?›
Through the OpenAI API.
What is the context window of o3 (2025-04-16)?›
200K tokens.
When was o3 (2025-04-16) released? Is there a newer version?›
Released 2025-04-16. It has been superseded by GPT-5.6 Sol.
Can o3 (2025-04-16) read images?›
It accepts text and images as input.
What is o3 (2025-04-16)?›
o3 (2025-04-16) is a language model from OpenAI, released Apr 2025.
What are the best alternatives to o3 (2025-04-16)?›
Gemini 3.8 Flash (cheaper), Claude Haiku 5.5 (better), DeepSeek V4 Pro 0813 (open weights).