跳转到主要内容

GPT-6.2 Sol (Max)

OpenAIProprietary

描述

GPT-6.2 Sol is OpenAI's efficient, versatile GPT-6.2 model for everyday work, from coding and writing to powering agents at scale. The API model id is gpt-6.2-sol. It accepts text and image input with text output, supports low, medium, high, xhigh, and max reasoning effort (but not none), and provides a 1,050,000-token context window (922,000 max input) with up to 128,000 output tokens. Responses API tools include web and file search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, MCP, and tool search; it also supports streaming, function calling, structured outputs, and multi-agent delegation (beta). Standard per-million-token pricing is $2 input, $0.10 cached input, $2.50 cache writes (30-minute retention), and $10 output, unchanged from GPT-6.1 Sol. Prompts above 272K input tokens cost 2x input/cache and 1.5x output across the full request. Batch costs 50% of Standard; Fast costs 2x; Ultrafast costs 3 times the Standard rate through February 28, 2027, and 6 times the Standard rate starting March 1, 2027 (Pacific time). Launch benchmarks are OpenAI-reported; effort variants are recorded with each score.

发布日期
2026-11-17
参数规模
—
上下文长度
1.1M
支持模态
image, pdf, text

能力雷达图

57
general
60
coding
60
reasoning
85
science估算
60
agents
80
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
智能体能力模型榜43
57.0
LS
通用能力榜5
88.0
AA
科学能力6
83.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Agents' Last Exam73.0%自报
AutomationBench v1.0.641.2%自报

Code

PatchBench75.6%自报
SecureSWE55.6%自报

General

LifeVal83.8%自报
GDPval v246.9%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)96.0%自报
Terminal-Bench-Science 0.168.0%自报
Vals Science Index58.5%自报
FrontierCode 2.043.8%自报

AA 评测指数

(Artificial Analysis)
Engineering(Artificial Analysis)
61.2
Strategy And Ops
59.4
Economics
57.4
Intelligence Index(Artificial Analysis)
57.3
Finance And Accounting
57.2
Legal
55.0
Healthcare And Medical
53.3

LLM Stats 分类评分

(LLM Stats (zeroeval))
Physics
100
Biology
100
Chemistry
100
Reasoning
60
General
60
Agents
60
Code
60
Tool Calling
60

定价

输入价格$2 / 1M tokens
输出价格$10 / 1M tokens
混合价格(3:1)$4 / 1M tokens
缓存读取价格$0.1 / 1M tokens
缓存写入价格$2.5 / 1M tokens

速度

Tokens/秒90.9
首Token延迟241.51s
首回答延迟241.51s

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1OpenAI主要
$2
$10

比较该模型在不同 API 供应商之间的定价。

外部链接