搜索“Agent”

Microsoft has released Microsoft-Decision-1, a decision model for routing, classification, verification and agent control. Microsoft-Decision-1 is a decision-scoring model that returns a calibrated probability for each fixed answer option instead of generated text. It is post-trained from Alibaba’s Qwen3.5-9B and available now in Microsoft Foundry and OpenRouter. . TL;DR Size: Built on Qwen3.5-9B; exact parameter count not disclosed. 32,768-token context window; Runs on: Hosted API only (Microso

匹配字段正文

编码任务，Gemini 4 Pro拿下88.7%，超过Astra的86.9%； GDPval-AA v2真实知识工作任务，它是唯一突破2000 Elo大关的模型，达到2064； Terminal-bench 2.1终端编码能力95.3%，全场最高；OSWorld-2.0计算机操作测试86.8%，同样排名第一。 在Terminal-Bench 4.0，专门考察Agent连续多步执行能力的测试，4 Pro与自家Flash的差距从上一代测试中的3.2%，直接拉大到13.9%。 换句话说，任务越复杂、链路越长、步骤越多，4 Pro的优势就越明显。 这恰恰是当前所有AI Agent最致命的短板——在需要持续串联多步动作、维护长上下文、反复读取状态并重新规划时，绝大多数模型都会出现严重的性能衰减。 而Gemini 4 Pro，似乎在这一点上找到了突破口。 价格方面更是让人意外。每百万Token输入仅2.25美元、输出11.25美元，在顶级旗舰中堪称“价格屠夫”。 黑进三家公司 内部Gemini干的 就在所有人还在为“机械蝴蝶”惊叹时，一个更令人脊背发凉的消息传了出来。 Google内部模型，可能是

匹配字段正文

hosting needs separate permission; No Turbo-specific benchmark exists yet; base Qwen-Image-2.1 scores 60.28 on Qwen-Image-Bench Asif Razzaq Asif RazzaqGoogle Cloud Launches Gemini Agent, One Universal Agent for Enterprise Work; Asif RazzaqJetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents; Asif RazzaqPerplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA; Asif RazzaqWhat Happens When a Trusted Model Repo Changes? Unsloth Studio Re-Che

匹配字段正文

ut in simulation, packing 1.46M standard cells, 0.277 MB of SRAM, and an INT4 MAC array with fused dequantization. A chip built by a model, for a model, reflects K3's long-horizon agentic capabilities. Coding for Research Kimi K3 bridges scientific literature and executable code, autonomously implementing, validating, and analyzing complex computational research workflows. In one case, Kimi K3 completed in about two hours what would typically require one to two weeks of work by an experienced re

匹配字段正文

Today, we are introducing Kimi K2 Thinking, our best open-source thinking model. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities. Kimi K2 Thinking can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve compl

匹配字段正文

Update(0905)：We have an updated weight that enhances agentic coding and supports 256K context，see here Kimi K2 is our latest Mixture-of-Experts model with 32 billion activated parameters and 1 trillion total parameters. It achieves state-of-the-art performance in frontier knowledge, math, and coding among non-thinking models. But it goes further — meticulously optimized for agentic tasks, Kimi K2 does not just answer; it acts. And now, it is within your reach. Today, we are open-sourcing: Kimi-K

匹配字段正文

. Bigger savings. Compared with the previous generation, V4.1-Flash's KV cache needs just: 🔹 1/4 the HBM 🔹 1/8 the SSD storage Cache-hit charges often account for a large share of agent costs. Compressing the cache cuts those costs significantly. ⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support. Set your model to deepseek-flash. 🔹 V4-Flash & V4-Flash-Vision-Exp are retired. For compatibility, deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to V4.1-

匹配字段正文

DeepSeek-V4-Pro GA Release 2026/08/13 We’re launching DeepSeek-V4-Pro today! 🚀 🔷 Major Agent upgrades with strong production gains! 🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, max for complex tasks. 🔷 Native OpenAI Responses API support, optimized for Codex with one-click setup. V4 Pro is now available on app/web. Try it via “Expert Mode”. V4 Pro is also available via API. Model names remain unchanged—please refer to the API docs for s

匹配字段正文

DeepSeek-V3.2 Release 2025/12/01 🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents! 🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API; 🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now; 📄 Tech report: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf 🔹 V3.2: Balanced inference vs. length. Your daily driver at GPT-5 level performance; 🔹 V3.2-Speciale: Maxed-

匹配字段正文

2-bit GGUF of Qwen3.8-27B that fits in 7.89 GB. The full BF16 model needs 54 GB. Underdog tuned the compression to protect tool calling, the skill that turns a chat model into an agent. For developers, that means a 27B-class agent model that runs in stock llama.cpp. TL;DR Size: 27B dense parameters. 7.89 GB GGUF versus 54 GB for BF16; Runs on: stock llama.cpp and apps built on it, with full GPU offload. Optional 629 MB or 928 MB vision add-on; Performance: 96% average retention across 9 benchma

匹配字段正文

JetBrains has released Mellum2.1, an open model built for coding agents and fast sub-agents. Mellum2.1 is a 12B mixture-of-experts thinking model from JetBrains that activates 2.5B parameters per token. It ships under Apache 2.0 on Hugging Face. The architecture is unchanged from Mellum2. The upgrade comes almost entirely from reinforcement learning (RL) in real software environments. The result is a small, self-hostable model that explores a repository, edits files, and checks its own changes.

匹配字段正文

Odyssey-3 is a foundation world model, enabling many applications in physical AI, human experiences, and even how we train intelligences. We're particularly excited by agents learning from experience inside Odyssey-3, working to accomplish objectives. https://t.co/mdPUBOiWqX

匹配字段正文

effort settings; Cost figures are provisional. Artificial Analysis does not yet model the 5x price step above 100K tokens. Cost-per-task numbers will follow; AA-Briefcase (private agentic knowledge-work eval): 1578 Elo. That is ahead of Kimi K3 and GLM-5.3, and comparable to Muse Spark 1.3 at max; Terminal-Bench 4.0: 33%, up from 0% for Haiku 4.5.Level with GLM-5.3 Flash; Ahead of Gemini 3.8 Flash (20%) and GPT-6 Luna (13%); Knowledge versus hallucination (AA-Omniscience):ModelAccuracyHallucinat

匹配字段正文

Step 5 Preview now exists where you build. Now live on @OpenRouter. A week of free access is rolling out today across @opencode, @cline , @NousResearch, @kilocode, and more. Flagship-tier intelligence for agentic and professional work, at substantially lower task cost. Keep your workflow. Switch your model. Try Step 5 Preview on OpenRouter: https://t.co/Z1nOT0rDj8

匹配字段正文

Anthropic has released Claude Haiku 5.5, its cheapest and fastest small model to date. It targets high-volume work like summaries, compaction, classification and subagent tasks. It keeps a 1M token context window and up to 128K output tokens. Pricing starts at $0.10 per million input tokens and $0.50 per million output tokens. That is 90% below Claude Haiku 4.5 for prompts up to 100K tokens. Is it deployable? Yes, as a hosted API. Haiku 5.5 is generally available on the Claude API, Amazon Bedroc

匹配字段正文

space. Best Use Cases The best fit is visual document search over PDFs, slides and scanned reports; Low-latency search: index in the cloud with 9B, then query on-device with 0.6B; Agentic RAG over large PDF or web collections The 0.6B model fits edge devices; the 9B model is built for index-time quality; Best score: 92.4% on MADQA. Weakest: 61.2% on ViDoRe v3 Markdown; 0.6B queries over a 9B index beat 0.6B on both sides; Storage growth and self-reported scores are the main caveats [Sponsored] T

匹配字段正文

た。 Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries. https://t.co/RB9xCWo4Db— ClaudeDevs (@ClaudeDevs) October 7, 2026 大量の反復処理やサブエージェントでの利用を想定 Haiku 5.5は、要約、分類、会話履歴の圧縮、データベースへの問い合わせといった範囲の限られた作業を、低コストで大量に処理する用途に向けたモデル。Anthropicは、コーディングでOpus 5.5やSonnet 5.5と組み合わせ、作業の一部を任せる

匹配字段正文

are one state in a single call. Every response reports output tokens: 0. Liquid AI recommends d1 for routing, moderation, intent classification, reranking, LLM-as-a-judge scoring, agent guardrails, and visual inspection. Neither checkpoint is a chat model. How are d1-3B and d1-omni-600M built? d1-3B has 3.12B parameters and starts from LFM2.5-VL-3B, a decoder-only vision-language model. Liquid AI averaged the weights of LFM2.5-2.6B with that model’s text backbone. It then fine-tuned several chec

匹配字段正文

ore tokens than GPT-6 Luna: Haiku 5.5 (high) scores 38 with 55k tokens per task against 38 with 50k for Luna (max), and the gap widens at lower effort settings ➤ Highly capable at agentic knowledge work: on AA-Briefcase, our private evaluation for realistic knowledge work tasks, Haiku 5.5 (max) reaches 1578 Elo, ahead of models including Kimi K3 and GLM-5.3, and comparable to Muse Spark 1.3 (max) ➤ Improvements on terminal use: on Terminal-Bench 4.0 it scores 33%, up from 0% for Haiku 4.5. This

匹配字段正文

Since computer use burns through large amounts of tokens, a cheap, fast model like Haiku 5.5 is a natural fit. It scores 72.4 percent on OSWorld-2.1, up from 15.7 percent. On the agentic coding benchmark Terminal-Bench 4.0, it reaches 39.2 percent while Haiku 4.5 scored zero. Anthropic also lists OpenAI's budget model GPT-6 Luna as a comparison, and Haiku 5.5 leads across every tested category. Sonnet 5.5 reference scores show, however, that Haiku 5.5 still falls well behind Anthropic's larger

匹配字段正文