跳转到主要内容

GPT-5.1 (Non-reasoning)

OpenAIGPTProprietary

描述

GPT-5.1 Instant is the next iteration of GPT-5, designed to be more conversational than earlier chat models. It features improved instruction following and an adaptive reasoning capability that lets it decide when to think before responding. GPT-5.1 Instant offers clearer and more engaging interactions, reducing jargon and enhancing user comprehension. It demonstrates significant improvements in coding tasks, making it a valuable tool for developers. GPT-5.1 Auto routes each query to the model best suited for it, so users typically don't need to choose a model manually.

发布日期
2025-11-13
参数规模
上下文长度
400K
支持模态
image, text

能力雷达图

36
general
47
coding
42
reasoning
43
science
80
agents
90
multimodal

排行榜排名

领域#排名分数来源
代码能力榜242
47.0
AA
通用能力榜245
49.0
AA
科学能力307
44.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)88.1%自报

Code

SWE-Bench Verified76.3%自报

Communication

Tau2 Telecom95.6%自报
Tau2 Retail77.9%自报
Tau2 Airline67.0%自报

General

MMMU85.4%自报

Math

AIME 202598.4%自报
FrontierMath26.7%自报

Reasoning

BrowseComp Long Context 128k90.0%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
38.0
Intelligence Index(Artificial Analysis)
20.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.6
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.5
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Lcr(Artificial Analysis)
0.4
Ifbench(Google Research (2023))
0.4
Aime 25(MAA (Mathematical Association of America))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats 分类评分

(LLM Stats (zeroeval))
Multimodal
90
Physics
90
Search
90
Healthcare
90
Biology
90
Chemistry
90
Vision
90
Reasoning
80
Frontend Development
80
General
80
Code
80
Communication
80
Tool Calling
80
Math
60

定价

输入价格$1.25 / 1M tokens
输出价格$10 / 1M tokens
混合价格(3:1)$3.438 / 1M tokens
缓存读取价格$0.125 / 1M tokens

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

12 个供应商

最便宜: OpenAI最贵: Cortecs
供应商输入输出
1OpenAI最便宜
$0
$0.00001
2OpenCode Zen
$1.07
$8.5
3Jiekou.AI
$1.125
$9
4302.AI
$1.25
$10
5Abacus
$1.25
$10
6Helicone
$1.25
$10
7AIHubMix
$1.25
$10
8Azure Cognitive Services
$1.25
$10
9LLM Gateway
$1.25
$10
10Azure
$1.25
$10
11Pioneer
$1.25
$10
12Cortecs
$1.375
$10.96

比较该模型在不同 API 供应商之间的定价。

外部链接