GPT-5 Mini (2025-08-07)
Aug 2025
GPT-5 Mini (2025-08-07)Compare inon
Benchmarks of GPT-5 Mini (2025-08-07)27
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math5
Writing2
Legacy · saturated or no longer reported17
No benchmark matches
Rankingat high effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperClaude Haiku 5.5max×2.3-71%$0.21Remove sampling parameters+5BetterGPT-6 Lunamax+50%-71%$0.068Function calling only with none · Chat Completions+3
OpenDeepSeek V4 Pro 0813max+92%+188%$0.67No image input+5CheaperDeepSeek V4.1 Flash 1017maxOpen+92%-24%$0.26Pass back reasoning_content · Chat Completions+4CheaperGPT-5.4 Nano (2026-03-17)xhigh+88%-33%$0.20 / $1.25ModelScoreCostPer taskWhat changes
Claude Haiku 5.5max×2.3-71%$0.21Remove sampling parameters+5DeepSeek V4.1 Flash 1017maxOpen+92%-24%$0.26Pass back reasoning_content · Chat Completions+4GPT-5.4 Nano (2026-03-17)xhigh+88%-33%$0.20 / $1.25GPT-5.6 Lunamax+79%-35%$0.18GPT-6 Lunamax+50%-71%$0.068Function calling only with none · Chat Completions+3ModelScoreCostPer taskWhat changes
GPT-6 Lunamax+50%-71%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Terralow+13%+555%$0.14Prompts with >272K input tokensGPT-5.6 Lunamax+79%-35%$0.18Claude Haiku 5.5max×2.3-71%$0.21Remove sampling parameters+5GPT-5.6 Sollow+29%+1,064%$0.26ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+92%+188%$0.67No image input+5DeepSeek V4.1 Flash 1017maxOpen+92%-24%$0.26Pass back reasoning_content · Chat Completions+4
Kimi K3highOpen+54%+773%$3 / $15Sampling parameters are fixed+3
GLM 5.3maxOpen+54%+213%$2.01No image input+4GLM 5.2maxOpen-8%+213%$1.28No image inputModelScoreCostPer taskWhat changes
GPT-6 Astramax×3.1—$3.26Monitoring can return HTTP 403+2GPT-6.1 Solmax×2.8—$0.72Remove unsupported parameters+5GPT-5.5xhigh×2.6—$2.10Prompts with >272K input tokensGPT-5.5 Proxhigh×2.6—$30 / $180GPT-5.6 Solmax×2.5—$1.99GPT-5.4 Pro (2026-03-05)×2.5—$30 / $180No strict JSONGPT-6 Solmax×2.3—$1.04GPT-5 Pro (2025-10-06)×2—$15 / $120All OpenAI models →History
7 versionsBenchmarks
all categoriesChat & Knowledge
SimpleQA Verified v121.6#68
MATH Level 597.8#2
FrontierMath27.2#15
FrontierMath Tier 46.3#14
FrontierMath Tiers 1–3 (v2)46.7#48
FrontierMath Tier 4 (v2)12.2#48
Chess Puzzles24#45
GPQA Diamond · Epoch75#76
OTIS Mock AIME 2024 202586.7#56
Coding
SWE-rebench · all · December 1, 2025 to February 1, 202639.6#2
SWE-rebench · Go · December 1, 2025 to February 1, 20260#1
SWE-rebench · Java · December 1, 2025 to February 1, 20260#1
SWE-rebench · Rust · December 1, 2025 to February 1, 20260#1
SWE-rebench · Python · December 1, 2025 to February 1, 202639.6#2
SWE-rebench · TypeScript · December 1, 2025 to February 1, 20260#1
FAQ
How much does GPT-5 Mini (2025-08-07) cost?›
$0.25 per 1M input tokens and $2 per 1M output tokens.
Is GPT-5 Mini (2025-08-07) free to use?›
There is no free API; the cheapest paid price is $0.25 per 1M input tokens.
How good is GPT-5 Mini (2025-08-07), and what is it best at?›
#68 of 84 in Chat & Knowledge, #19 of 24 in Coding, #8 of 39 in Agents & Tool Use, #59 of 96 in Writing & Language.
Is GPT-5 Mini (2025-08-07) better than Qwen3.7 Max?›
On Chess Puzzles, GPT-5 Mini (2025-08-07) scores 24 vs 26 — lower.
How can I use GPT-5 Mini (2025-08-07)?›
Through the OpenAI API.
What is the context window of GPT-5 Mini (2025-08-07)?›
400K tokens.
When was GPT-5 Mini (2025-08-07) released? Is there a newer version?›
Released 2025-08-07. It has been superseded by GPT-5.6 Terra.
Can GPT-5 Mini (2025-08-07) read images?›
It accepts text and images as input.
What is GPT-5 Mini (2025-08-07)?›
GPT-5 Mini (2025-08-07) is a language model from OpenAI, released Aug 2025.
What are the best alternatives to GPT-5 Mini (2025-08-07)?›
Claude Haiku 5.5 (cheaper), GPT-6 Luna (better), DeepSeek V4 Pro 0813 (open weights).