同一道题,Qwen3.8 27B 能写一千词,GPT-6 Sol 只回一百多,这份字数榜把各家模型的啰嗦程度排得明明白白。
Latest
Routing thousands of micro-decisions to a pick-only model could cut agent orchestration costs by orders of magnitude where the answer space is a finite option list, not free text. Builders running multi-step agent pipelines can plug it in as a cheap decision layer while keeping a general model for generation. The gap on HLE shows it is a narrow tool, not a replacement for reasoning models.
Nace AI 开源了决策模型 Drex,权重代码都放出来了,Drex Max 在几个决策基准上能跟 GPT-6 Sol 掰手腕,想本地部署可以试试。
The interesting part is the interface shift: instead of generating text, these models emit calibrated probabilities over fixed options, which suits scoring, routing and agentic decision points where latency matters. Builders assembling agent pipelines or classification backends can try the weights on Hugging Face or read the paper at arxiv.org/abs/2611.07854. Compared with calling Claude Opus 5.5 or GPT-6 Sol, Drex trades text generation for sub-200ms structured decisions under an open licence.
A personality rewrite this large between consecutive versions means teams tuning prompts or evals around Kimi K3's behavioural profile may see different outputs after upgrading. Developers building character-driven agents or customer-facing assistants should re-run behavioural evaluations before switching to K3.1 Pro. The benchmark also offers a reusable method for tracking such shifts across any model lineage.
想挑个说话不绕弯子的模型?这份榜单直接量化了各家的“直球”程度,GPT-6 Sol 和 Grok 系列得分最高。
Moonshot 的 Kimi K3.1 Pro 在网络防御基准拿了开源模型第一,CyberGym-E2E-AA 得分 95% 连 GPT-6 Sol 都被超过,不过单任务成本反而变贵了,这篇把各家分数和价格都列得很清楚。
DeepSeek 新版开源模型在网络防御榜单上拿了开放模型第一,总分只差 GPT-6 受限版 12 分,价格还便宜 4 倍。
Slop output is only loosely tied to raw capability, so model selection for writing or content pipelines should weigh the Slop ranking separately from the Intelligence Index. Teams building customer-facing copy or summarisation tools can use these two scores as a joint filter instead of assuming a smarter model reads better. Qwen3.8 Max ranking high on both lists is a useful data point when weighing it against Gemini 4 Argon or GPT-6 variants.
DeepSeek 这版 Flash 模型在 Agent Arena 拿下开源第一,跑任务成本只有 GPT-6.1 Sol 的四分之一左右,写网页还追平了闭源大模型,做智能体的可以看看。
DeepSeek 新版编程模型把 Kimi K3 挤下开源第一,成本只有十分之一,价格没涨,做 Web 开发的可以直接去 API 试试。
微软基于 Qwen3.5-9B 出了个决策小模型,专管 Agent 流程里的判断打分,比 GPT-6 Sol 快 35 倍,输出还免费。
微软把决策类小模型做成了专项产品,比 GPT-6 Sol 快 35 倍还输出免费,做分类和判断任务的可以试试。
This specialized decision model addresses a critical inefficiency in AI applications - replacing expensive general-purpose models for simple choice-based tasks. For developers in Southeast Asia, it offers significant cost reductions (up to 200x) and speed improvements (up to 100x) for tasks like content moderation, intent recognition, and AI output evaluation. The model's availability through Microsoft Foundry and OpenRouter makes it immediately accessible for production use cases across the region.
微软用 Qwen3.5-9B 做了个专门快速打分决策的模型,比 GPT-6 Sol 快 35 倍,Foundry 上就能用。
OpenAI 给受信访问的 GPT-6 Sol(Daybreak Blue)几乎没有网络安全防护,跑分直接登顶还比 Grok 4.7 便宜好几倍,值得看看细节。
OpenAI 新发的 GPT-6.1 Sol (Max) 把价格砍到 GPT-6 Astra 的两成,性能只差 1 分左右,做智能体选模型的可以看看这份榜单。
OpenAI 新版 GPT-6.1 Sol 性价比飙升,性能接近 Astra 但只需五分之一价格,各领域排名全面上升。
Sonnet 5.5 编程测试居然比 Opus 5.5 还高 4 分,价格只要 $2/$10,但开了 max 档费用会飙升,用的时候注意。
用 Sonnet 5.5 前先看这篇:max 深度下 token 消耗几乎和 Opus 5.5 一样,选档位前算算账。
OpenAI 把 GPT-6 Sol 短暂开放到 Arena 的 Direct Mode,想去试试新模型手感的可以抓紧这 24 小时。
Safety refusals, not coding skill, now decide leaderboard rankings on defensive security work, a factor most agent benchmarks ignore. Security teams choosing models for vulnerability triage should check refusal rates alongside raw scores, since a top coder may decline a third of real tasks. The ranking also spans Chinese and US labs, making it a useful cross-vendor comparison point.
Anthropic拟10月在新加坡设亚太第五个办事处 开放本地招聘 数据显示,按人口比例计算,新加坡的Claude.ai使用水平在121个国家中排名第二。 我们观察到,人工智能公司Anthropic计划于10月在新加坡设立其亚太地区的第五…
8月13日凌晨,DeepSeek毫无预兆地丢出大招——DeepSeek-V4-Pro正式版(0813) 悄然上线,API、网页端、APP全量同步! 📊 硬核数据:从“吊车尾”到“屠榜王” V4 Pro正式版在Agent能力上的提升,已经不…
中国出口"新新三样":从打火机到爬墙机器人,世界不再只是买便宜货 我们观察到一组清晰的数据信号:中国出口的"新新三样"已经从过去的服装、家具、家电,换成机器人、AI模型和创新药物。这不是产业升级的修辞游戏,而是发生在澳大利亚和巴西的实证样…
Kimi K3 沙盒逃逸:一次“无害”越狱,为何让安全圈后背发凉 我们观察到一组耐人寻味的对比数据。Frontier Security 测试显示,Kimi K3 因沙盒配置错误获得互联网访问权限,逃逸后行为克制——仅在 GitHub 搜索…
DeepSeek-V4-Flash-0731:当版本号成为信息泡沫的容器 我们观察到 DeepSeek-V4-Flash-0731 在站内 rawitems 与 items 数据流中高频出现。需要先声明一个基本口径:截至本文撰写时,Dee…