GPT-5 mini (high)
OpenAIGPTProprietary
描述
A faster, more cost-efficient version of GPT-5 for well-defined tasks. Great for well-defined tasks and precise prompts with high reasoning capabilities at reduced cost.
發布日期
2025-08-07
參數規模
—
上下文長度
400K
支援模態
image, text
能力雷達圖
38
general
42
coding
89
reasoning
55
science
75
agents
85
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Math
AIME 2025
91.1%自報
HMMT 2025
87.8%自報
FrontierMath
22.1%自報
Reasoning
GPQANYU + Cohere + Anthropic (2023)
82.3%自報
Humanity's Last Exam
16.7%自報
AA 評測指數
(Artificial Analysis)Math Index(Artificial Analysis)90.7
Aime 25(MAA (Mathematical Association of America))90.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))83.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))83.7
Gpqa(NYU + Cohere + Anthropic (2023))82.8
Ifbench(Google Research (2023))75.4
Lcr(Artificial Analysis)72.3
Tau2(Sierra + U Toronto + Vector Institute (2025))68.4
Scicode(UIUC + Argonne National Lab (2024))39.0
Terminalbench Hard(Stanford × Laude Institute (2026))33.3
Hle(Center for AI Safety + Scale AI (2025))21.5
Intelligence Index(Artificial Analysis)16.8
Coding Index(Artificial Analysis)15.6
Tau Banking15.5
Terminalbench V2 13.7
Terminalbench V4 00.0
LLM Stats 分類評分
(LLM Stats (zeroeval))Physics80
Biology80
Chemistry80
General60
Math50
Reasoning50
Vision20
定價
輸入價格$0.25 / 1M tokens
輸出價格$2 / 1M tokens
混合價格(3:1)$0.688 / 1M tokens
快取讀取價格$0.025 / 1M tokens
速度
Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s
供應商價格排行
供應商價格排行
1 個供應商
供應商輸入輸出
1OpenAI
$0
$0
比較該模型在不同 API 供應商之間的定價。