Explore tools, prompts, skills, news and resources related to SWE-bench 第2页.
Prompt works related to SWE-bench 第2页
Latest articles, prompts, use cases and editorial content about SWE-bench 第2页
Liquid AI introduced LFM3, a family of six open-weight 2B-class models built on one tri-hybrid backbone for text, vision, audio, omni and decision tasks. The 1.7B text model runs in about 1GB at 4-bit with a 256K context...
UC Berkeley's Sky Computing Lab released LEANN, an open-source vector index that stores a pruned graph instead of full embeddings and recomputes embeddings only for nodes on the search path. Benchmarks show a 60 mil...
Researchers from Tsinghua University and CUHK have open-sourced AKV, an Apache-2.0 serving system that lets LLM agents drop and reposition KV cache entries instead of summarizing text history. AKV extends SGLang's r...
Nanbeige LLM Lab, part of the recruitment platform BOSS Zhipin, released Nanbeige4.3-33B on Hugging Face under Apache 2.0. It is a 33B dense text model with a 524,288-token context window, aimed at agentic coding and off...
Recursive Superintelligence released Flint, a text-only mixture-of-experts coding model with 39.8B total and roughly 2.5B active parameters, under Apache 2.0 on Hugging Face. It targets coding agents, supports reasoning...
At GTC Berlin, NVIDIA detailed its local AI hardware and software stack, including RTX Spark PCs for personal agents, DGX Spark systems that can now cluster up to eight units with 1TB of unified memory, and DGX Station f...
Inception has launched Mercury 3, a diffusion language model that refines answers in parallel rather than token by token, claiming 1,068 tokens per second on NVIDIA GPUs and a 1M-token context window. Inception's ow...
NVIDIA released Nemotron 3.5 Super VL, an open vision-language agent model with 120B total parameters and 12B active per token in a mixture-of-experts design, supporting text, image, document and video input with up to 1...
Microsoft Research Asia released Agent Lightning v1.0, a lightweight framework that implements a complete agentic reinforcement learning control plane in roughly 3,500 lines of code. It introduces Harnessed Agentic RL, w...
Liquid AI released LFM2.5-24B-A2B, an open-weight 24B-parameter Mixture-of-Experts reasoning model with about 2B active parameters and 131,072-token context, targeted at local agent loops. It runs via GGUF/MLX on laptops...
Headline: DeepSWE Benchmark Revolutionizes AI Coding Rankings: GPT-5.5 Dominates as Claude Opus Accused of "Cheating" on Legacy TestsThe landscape of AI code generation has undergone a significant shift this we...
Adaption Launches AutoScientist, an AI Tool That Lets Models Train ThemselvesFor years, AI researchers have anticipated a breakthrough moment when AI systems could improve themselves more effectively than humans can. Wit...
Ant Group's Inclusion AI has officially released the weights for its flagship large language model, Ling-2.6-1T. This trillion-parameter MoE (Mixture of Experts) model is now available to the public under a perm...
After three years of stealth development and securing $626 million in funding, AI coding specialist Poolside has officially released its first programming models to the public. Founded in 2023 with a...
SemiAnalysis, a prominent semiconductor and AI analytics firm, has released a comprehensive horizontal evaluation of leading AI programming assistants, covering GPT-5.5, Opus 4.7, and DeepSeek V4. The core...
Discover tools, products and platforms related to SWE-bench 第2页