GPT-6.1 Sol发布说明
执行中调整方向，即时响应
Tibo 表示，模型的方向调整功能（steering）已改为即时响应：用户在模型执行过程中调整要求，模型能更快跟进，实时纠正方向，减少沿错误方向继续投入的工作。他同时宣布发布 GPT-6.1 Sol ultrafast，并称它与这项改进配合良好。
查看资料模型能力评测
重点更新
GPT-6发布说明
Intelligent UI 进入日常聊天
OpenAI 在 ChatGPT 全球推出带 Intelligent UI 的 GPT-6，今天覆盖 Plus、Pro、Business 和 Enterprise，明天起扩展至 Free 与 Go。Plus、Pro、Business 和 Enterprise 使用 GPT-6 Sol，Free 与 Go 使用 GPT-6 Luna；此次更新仅适用于 Chat tab，Work 和 Codex 的模型不变。
查看资料Gemini 3.8 Live发布说明
边调用工具，边进行音视频交流
Google 于9月24日推出 Gemini 3.8 Live with Live Avatar，结合近实时视频生成与语音，在后台异步调用工具时可继续交流。官方称其支持97种语言，当日已在 Gemini Enterprise 提供；自定义 Avatar 可由参考图生成，但创建目前仅向企业白名单开放。音视频输出包含 SynthID 水印，尚未宣布向免费个人用户普遍开放。
查看资料语言对话 · Arena ↗
amazon-nova-experimental-chat-26-02-10
关闭详情'%3e%3cmask%20height='32'%20id='lobe-icons-nova-0-_R_0_'%20maskUnits='userSpaceOnUse'%20style='mask-type:luminance'%20width='32'%20x='0'%20y='0'%3e%3cpath%20d='M31.8%200H0v32h31.8z'%20fill='%23fff'%3e%3c/path%3e%3c/mask%3e%3cmask%20height='32'%20id='lobe-icons-nova-1-_R_0_'%20maskUnits='userSpaceOnUse'%20style='mask-type:alpha'%20width='32'%20x='0'%20y='0'%3e%3cpath%20d='m17.865%2023.28%201.533%201.543c.07.07.092.175.055.267l-2.398%206.118A1.24%201.24%200%200%201%2015.9%2032c-.51%200-.969-.315-1.155-.793l-3.451-8.804-5.582%205.617a.246.246%200%200%201-.35%200l-1.407-1.415a.25.25%200%200%201%200-.352l6.89-6.932a1.3%201.3%200%200%201%20.834-.398%201.25%201.25%200%200%201%201.232.79l2.992%207.63%201.557-3.977a.248.248%200%200%201%20.408-.085zm8.224-19.3-5.583%205.617-3.45-8.805a1.24%201.24%200%200%200-1.43-.762c-.414.092-.744.407-.899.805l-2.38%206.072a.25.25%200%200%200%20.055.267l1.533%201.543c.127.127.34.082.407-.085L15.9%204.655l2.991%207.629a1.24%201.24%200%200%200%202.035.425l6.922-6.965a.25.25%200%200%200%200-.352L26.44%203.977a.246.246%200%200%200-.35%200zM8.578%2017.566l-3.953-1.567%207.582-3.01c.49-.195.815-.685.785-1.24a1.3%201.3%200%200%200-.395-.84l-6.886-6.93a.246.246%200%200%200-.35%200L3.954%205.395a.25.25%200%200%200%200%20.353l5.583%205.617-8.75%203.472a1.25%201.25%200%200%200%200%202.325l6.079%202.412a.24.24%200%200%200%20.266-.055l1.533-1.542a.25.25%200%200%200-.085-.41zm22.434-2.73-6.08-2.412a.24.24%200%200%200-.265.055l-1.533%201.542a.25.25%200%200%200%20.084.41L27.172%2016l-7.583%203.01a1.255%201.255%200%200%200-.785%201.24c.018.317.172.614.395.84l6.89%206.931a.246.246%200%200%200%20.35%200l1.406-1.415a.25.25%200%200%200%200-.352l-5.582-5.617%208.75-3.472a1.25%201.25%200%200%200%200-2.325z'%20fill='%23fff'%3e%3c/path%3e%3c/mask%3e%3cg%20mask='url(%23lobe-icons-nova-1-_R_0_)'%3e%3cpath%20d='M-2.915%2034.125h37.448V-2.109H-2.915z'%20fill='url(%23lobe-icons-nova-2-_R_0_)'%3e%3c/path%3e%3c/g%3e%3c/g%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-nova-2-_R_0_'%20x1='33.663'%20x2='-2.086'%20y1='33.633'%20y2='-1.901'%3e%3cstop%20stop-color='%23ff6200'%3e%3c/stop%3e%3cstop%20offset='.399'%20stop-color='%23e433ff'%3e%3c/stop%3e%3cstop%20offset='.96'%20stop-color='%236842ff'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
amazon · 语言对话 · 2026-10-08
- Arena 评分
- 1426.5
- 来源名次
- 116
- 对战票数
- 3,523
- 评分区间
- 1416.8–1436.2
偏好评分；区间重叠时差异未必稳定。
模型许可：Proprietary。
原始成绩 ↗414 个模型
| 模型／机构 | Arena 评分 | 对战票数 |
|---|---|---|
gpt-5.2-high#101 · openai | 1437.21434–1441 | 49,685 |
longcat-flash-chat-2602-exp#102 · meituan | 1436.41432–1441 | 29,306 |
deepseek-v4-flash#103 · deepseek | 1436.01432–1440 | 52,047 |
gpt-5.2#104 · openai | 1435.51432–1439 | 83,928 |
gpt-5-high#105 · openai | 1434.71430–1439 | 31,723 |
qwen3-max-preview#106 · alibaba | 1434.31430–1439 | 27,379 |
mimo-v2.5#107 · xiaomi | 1433.71429–1438 | 47,402 |
glm-5v-turbo#108 · zai | 1433.51427–1440 | 10,492 |
gemini-3.1-flash-lite-preview#109 · google | 1432.91429–1437 | 64,257 |
o3-2025-04-16#110 · openai | 1431.71428–1435 | 58,913 |
mimo-v2-omni#111 · xiaomi | 1430.81425–1436 | 20,667 |
grok-4-1-fast-reasoning#112 · xai | 1430.41427–1434 | 57,574 |
kimi-k2.5-instant#113 · moonshot | 1430.41424–1437 | 8,378 |
kimi-k2-thinking-turbo#114 · moonshot | 1430.11427–1433 | 63,390 |
mistral-large-4#115 · mistral | 1429.31420–1439 | 4,179 |
amazon-nova-experimental-chat-26-02-10#116 · amazon | 1426.51417–1436 | 3,523 |
mistral-medium-3.5#117 · mistral | 1426.41420–1433 | 11,803 |
gpt-5-chat#118 · openai | 1426.31422–1431 | 31,203 |
claude-opus-4-20250514-thinking-16k#119 · anthropic | 1426.31422–1431 | 35,913 |
nvidia-nemotron-3-ultra-550b-a55b-nvfp4#120 · nvidia | 1426.11419–1433 | 11,571 |
'%20fill-rule='nonzero'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20id='lobe-icons-qwen-_R_0_'%20x1='0%25'%20x2='100%25'%20y1='0%25'%20y2='0%25'%3e%3cstop%20offset='0%25'%20stop-color='%236336E7'%20stop-opacity='.84'%3e%3c/stop%3e%3cstop%20offset='100%25'%20stop-color='%236F69F7'%20stop-opacity='.84'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
'%3e%3c/path%3e%3cpath%20d='M20.616%2010.835a14.147%2014.147%200%2001-4.45-3.001%2014.111%2014.111%200%2001-3.678-6.452.503.503%200%2000-.975%200%2014.134%2014.134%200%2001-3.679%206.452%2014.155%2014.155%200%2001-4.45%203.001c-.65.28-1.318.505-2.002.678a.502.502%200%20000%20.975c.684.172%201.35.397%202.002.677a14.147%2014.147%200%20014.45%203.001%2014.112%2014.112%200%20013.679%206.453.502.502%200%2000.975%200c.172-.685.397-1.351.677-2.003a14.145%2014.145%200%20013.001-4.45%2014.113%2014.113%200%20016.453-3.678.503.503%200%20000-.975%2013.245%2013.245%200%2001-2.003-.678z'%20fill='url(%23lobe-icons-gemini-1-_R_0_)'%3e%3c/path%3e%3cpath%20d='M20.616%2010.835a14.147%2014.147%200%2001-4.45-3.001%2014.111%2014.111%200%2001-3.678-6.452.503.503%200%2000-.975%200%2014.134%2014.134%200%2001-3.679%206.452%2014.155%2014.155%200%2001-4.45%203.001c-.65.28-1.318.505-2.002.678a.502.502%200%20000%20.975c.684.172%201.35.397%202.002.677a14.147%2014.147%200%20014.45%203.001%2014.112%2014.112%200%20013.679%206.453.502.502%200%2000.975%200c.172-.685.397-1.351.677-2.003a14.145%2014.145%200%20013.001-4.45%2014.113%2014.113%200%20016.453-3.678.503.503%200%20000-.975%2013.245%2013.245%200%2001-2.003-.678z'%20fill='url(%23lobe-icons-gemini-2-_R_0_)'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-0-_R_0_'%20x1='7'%20x2='11'%20y1='15.5'%20y2='12'%3e%3cstop%20stop-color='%2308B962'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%2308B962'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-1-_R_0_'%20x1='8'%20x2='11.5'%20y1='5.5'%20y2='11'%3e%3cstop%20stop-color='%23F94543'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%23F94543'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-gemini-2-_R_0_'%20x1='3.5'%20x2='17.5'%20y1='13.5'%20y2='12'%3e%3cstop%20stop-color='%23FABC12'%3e%3c/stop%3e%3cstop%20offset='.46'%20stop-color='%23FABC12'%20stop-opacity='0'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
数据来源
用户偏好评分，非正确率。下方小字为置信区间；临时成绩状态见原榜。本站选取 overall 分类、翻译字段并舍入显示，原始值保留。
每日 08:30 同步 · 最近成功：2026/10/11 08:26（北京时间）