Model Detail
needle
▲ 12.4%needle is a code generation model with 15M parameters released by Cactus-Compute. Distributed under the permissive mit license.
needle ships with 15M parameters. The mit license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of needle have moved +12.4% over the past 24 hours, +94.2% over the trailing thirty days. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
needle is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs
arXiv:2601.02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctuates significantly depending on how information is distributed in real-world corpora. We investigate
Finding Needles in the Haystack: Transductive Active Labeling in Ecology
arXiv:2606.03821v2 Announce Type: replace Abstract: Active learning is now standard practice in labeling ecological data, enabling ecologists to quickly process large volumes of field data to understand and monitor natural environments. Current practices evaluate active learning inductively, estimat
CmdNeedle: Measuring the Incompleteness of Command Denylists for AI Agents
arXiv:2606.15549v1 Announce Type: cross Abstract: The adoption of AI agents is increasing rapidly. Terminal AI agents, i.e., AI agents that run in terminal environments, are a widely used type of AI agents. Terminal AI agents rely heavily on shell command execution to interact with the host systems.
Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research
arXiv:2606.01364v1 Announce Type: cross Abstract: The attack surface of a modern operating system is a haystack: thousands of signed binaries and millions of functions, almost none relevant to any given vulnerability. A human analyst or an LLM agent must pick the function worth reading before analyz
VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes
arXiv:2605.26380v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such scores do not necessarily imply faithful use of visual evidence. Prior studies have identified thre
