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 ↗
gemini-2.5-pro
关闭详情'%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}
google · 语言对话 · 2026-10-08
- Arena 评分
- 1445.5
- 来源名次
- 86
- 对战票数
- 125,379
- 评分区间
- 1443.0–1447.9
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 |
|---|---|---|
claude-opus-4-1-20250805#81 · anthropic | 1448.01445–1451 | 77,252 |
mimo-v2-pro#82 · xiaomi | 1447.71443–1452 | 25,447 |
Step 5 Preview#83 · stepfun | 1447.31439–1456 | 4,799 |
gpt-5.4-mini-high#84 · openai | 1447.11443–1451 | 63,493 |
ernie-5.0-0110#85 · baidu | 1446.31442–1450 | 36,525 |
gemini-2.5-pro#86 · google | 1445.51443–1448 | 125,379 |
gpt-4.5-preview-2025-02-27#87 · openai | 1444.61439–1450 | 14,547 |
qwen3.6-plus#88 · alibaba | 1443.31439–1447 | 48,208 |
chatgpt-4o-latest-20250326#89 · openai | 1442.71440–1446 | 81,927 |
grok-4.7-xhigh#90 · xai | 1442.71436–1450 | 8,780 |
gpt-6-luna-max#91 · openai | 1442.61438–1448 | 28,632 |
qwen3.5-397b-a17b#92 · alibaba | 1441.71439–1445 | 91,190 |
grok-4.3#93 · xai | 1441.61438–1445 | 71,448 |
glm-4.7#94 · zai | 1441.21435–1447 | 12,256 |
inkling#95 · thinky | 1441.01437–1445 | 37,744 |
minimax-m3#96 · minimax | 1440.51437–1444 | 61,220 |
deepseek-v4-flash-high-preview#97 · deepseek | 1438.61435–1443 | 51,859 |
gpt-5.1#98 · openai | 1438.51435–1442 | 44,441 |
qwen3.8-27b#99 · alibaba | 1438.11433–1443 | 20,711 |
gemma-4-26b-a4b#100 · google | 1437.61430–1445 | 6,092 |
'%20fill-rule='evenodd'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-stepfun-_R_0_'%20x1='1.646'%20x2='18.342'%20y1='1.916'%20y2='22.091'%3e%3cstop%20stop-color='%2301A9FF'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%230160FF'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
'%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}
'%20fill-rule='nonzero'%3e%3c/path%3e%3c/svg%3e){kind=small}
'%20fill-rule='evenodd'%3e%3c/path%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）