| Chatbot Arena 得分 |
|---|
| 1314(媒体报道) |
来自 OpenAI 的 chatgpt-4o-latest API 页面(ChatGPT 所用 GPT-4o 的别名,现已下线;价格为该页面当前标价)。Arena 得分来自 Tom's Guide 和 Beebom 的报道,领先 Gemini-1.5-Pro-Exp 17 分。 · 来源
Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Scored from OpenAI's chatgpt-4o-latest API page (the alias for the GPT-4o snapshot used in ChatGPT; opened this run, now shut down): 128,000-token context = 1; text and image input = 3; $5 input / $15 output per 1M tokens = $7.50 blended at 3:1 = 2.75, rounded to 3 (the page shows the current list price; the August 2024 launch price was not separately opened). Reasoning, coding and speed are null: no Artificial Analysis index or Terminal-Bench figure was opened and OpenAI published no speed; OpenAI said granular benchmarking of this change is an open research problem. Press reported a Chatbot Arena score of 1314, 17 points above Gemini-1.5-Pro-Exp. Independent reviews: 3 found (Tom's Guide, Beebom, DailyAI press reports; no hands-on test of this exact update). developers.openai.com
Now, though, a new version of ChatGPT-4o (20240808) has reclaimed the lead from its rivals with a score of 1314 — 17 points ahead of Gemini-1.5-Pro-Exp.
On the LMSYS leaderboard, the new ChatGPT model has reclaimed the top spot with a score of 1314 points.
Announcing an updated ChatGPT-4o model yesterday was unlikely to have been a coincidence.
这个标记会跟进新闻:它显示目前已知的情况,这里列出改了什么以及起因。
已编辑由 @AIDesk
读者上传的照片,与图钉带来源的媒体分开显示。你可以为吃到或看到的内容评分,在餐厅图钉上还能直接在照片上标记菜品。
第一项始终是图钉的来源。总体可信度是各份资料对上方所用开始和结束时间支持程度的加权平均;资料每比最新的一份旧 180 天,权重减半。
OpenAI 自己的模型发布说明将该条目日期定为 2024 年 8 月 12 日
Independent report on the August 2024 GPT-4o update in ChatGPT; its lead picture is used on this pin with credit to The Decoder.
有遗漏或错误吗?用你自己的话说明:能佐证此图钉的链接、不同的开始或结束日期及理由,或缺失、有误的信息。AI 会对照此图钉的来源进行核实,搜索更好的来源,并添加任何支持你说法的页面。图钉自身的来源仍然最重要。AI 也会查看图片:显示的是别的东西或显示效果差的图片会被移到后面或替换。
原标题: GPT-4o Update Rolls Out in ChatGPT