Search Results for "benchmarks" - Page 6
Sort By:
Showing 440 open source projects for "benchmarks"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
ADR
ADR secures enterprise AI agents through observability
ADR, short for Agentic AI Detection and Response, is an enterprise security system for monitoring and evaluating AI agents. It captures agent intent, tool activity, and execution traces from coding assistants, internal automations, and customer-facing agents. A normalized sensor layer provides observability across multiple agent tools and operating systems. ADR-Bench supplies more than 300 realistic tasks, 133 MCP servers, and coverage of 17 documented agent attack techniques. Its two-tier... -
2
BaseRT
Fastest LLM inference runtime for Apple Silicon
...Stable C interfaces connect the engine with Python, Node.js, Rust, and Swift applications. The repository contains the open CLI, format specifications, bindings, documentation, and benchmarks, while the prebuilt inference engine uses a separate license. -
3
Codex Autoresearch
A codex plugin for running optimization loops inside a codebase
Codex Autoresearch is an autonomous software improvement framework that enables AI coding agents to iteratively enhance codebases without continuous human input. The system operates in a loop where the agent modifies code, evaluates results against measurable metrics, and either keeps or discards changes based on performance. It generalizes the concept of autoresearch beyond machine learning, allowing optimization of test coverage, latency, lint errors, and overall code quality. Developers... -
4
Sail
A drop-in Apache Spark replacement written in Rust
...The framework is designed to operate across a variety of environments, including local machines, Kubernetes clusters, and cloud deployments, allowing flexible scaling based on workload requirements. It also emphasizes cost efficiency, with benchmarks showing significant performance improvements and reduced infrastructure usage compared to traditional systems. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
anti-distill
Anti-distillation for employee Skills
...The system is particularly relevant in contexts where models are exposed via APIs and risk being reverse-engineered through repeated querying. Its design reflects growing concerns around model security and competitive advantage in AI systems. It may also include experimental benchmarks to evaluate how resistant a model is to distillation attempts. Overall, anti-distill represents an emerging area of AI defense focused on safeguarding model behavior and preventing unauthorized replication. -
6
TTRL
Test-Time Reinforcement Learning
TTRL is an open-source framework for test-time reinforcement learning in large language models, with a particular focus on reasoning tasks where ground-truth labels are not available during inference. The project addresses the problem of how to generate useful reward signals from unlabeled test-time data, and its central insight is that common test-time scaling practices such as majority voting can be repurposed into reward estimates for online reinforcement learning. This makes the... -
7
MiroThinker
MiroThinker is an open source deep research agent
...The platform is optimized for research tasks such as financial forecasting, knowledge discovery, and large-scale information synthesis. MiroThinker has been evaluated on several agent benchmarks and has demonstrated strong performance on tests designed to measure deep research capabilities. -
8
browserable
Open source and self-hostable browser automation library for AI agents
Browserable is an open-source browser automation framework designed specifically for AI agents that need to interact with web interfaces in a human-like way. The project provides tools that allow automated agents to navigate websites, click buttons, fill out forms, and extract information from pages without manual scripting of each step. Built primarily in JavaScript, the framework offers both a developer-friendly SDK and a REST API that allow integration with AI applications and automation... -
9
KG-LLM-Papers
Papers integrating knowledge graphs (KGs) and large language models
KG-LLM-Papers is a curated academic resource that collects and organizes research papers exploring the intersection between knowledge graphs and large language models. The repository functions as a continuously updated index of scholarly work that investigates how structured knowledge representations can enhance the reasoning, factual accuracy, and interpretability of language models. It includes surveys, benchmark studies, and cutting-edge research that examine topics such as knowledge... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
CodeGen
Open-source model for program synthesis
CodeGen is a family of open-source large language models designed specifically for program synthesis and code generation tasks. Developed by Salesforce Research, the models are trained on large datasets containing both natural language and programming language content. This allows them to translate natural language descriptions into functional code across a variety of programming languages. CodeGen supports multi-turn program synthesis, meaning it can generate complex programs through a... -
11
ANE Training
Training neural networks on Apple Neural Engine via APIs
...It explores the internal software stack of the Apple Neural Engine by interfacing with private classes such as _ANEClient and compiling custom compute graphs in the MIL format. The project includes performance benchmarks and kernel breakdowns that show how different components of the training loop are distributed between the ANE and CPU. It is primarily intended as a research and educational proof of concept rather than a production library, highlighting what is technically possible with undocumented hardware access. -
12
FireRedASR
Open-source industrial-grade ASR models
FireRedASR is an industrial-grade family of open-source automatic speech recognition models designed to provide high-precision speech-to-text performance across languages including Mandarin, English, and various Chinese dialects, achieving new state-of-the-art benchmarks on public test sets. The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. ... -
13
mapcn
Beautiful map components, 100% Free, Zero config, one command setup
mapcn is a research-oriented project centered on mapping continuous control in reinforcement learning to structured policies using neural networks. It explores how high-dimensional action spaces can be decomposed into structured primitives that can be learned, composed, and reused across different tasks. The core idea is to enable agents to generalize learned behavior by representing continuous control policies in a compact, interpretable form that preserves smoothness and controllability.... -
14
CutLER
Code release for Cut and Learn for Unsupervised Object Detection
CutLER is an approach for unsupervised object detection and instance segmentation that trains detectors without human-annotated labels, and the repo also includes VideoCutLER for unsupervised video instance segmentation. The method follows a “Cut-and-LEaRn” recipe: bootstrap object proposals, refine them iteratively, and train detection/segmentation heads to discover objects across diverse datasets. The codebase provides training and inference scripts, model configs, and references to... -
15
SlowFast
Video understanding codebase from FAIR for reproducing video models
...Together, these two pathways complement each other, allowing the network to model both appearance and motion without excessive computational cost. The architecture is modular and supports tasks like action recognition, temporal localization, and video segmentation, performing strongly on benchmarks like Kinetics and AVA. The repository provides training recipes, pretrained models, and distributed pipelines optimized for large-scale video datasets. -
16
CLIP
CLIP, Predict the most relevant text snippet given an image
CLIP (Contrastive Language-Image Pretraining) is a neural model that links images and text in a shared embedding space, allowing zero-shot image classification, similarity search, and multimodal alignment. It was trained on large sets of (image, caption) pairs using a contrastive objective: images and their matching text are pulled together in embedding space, while mismatches are pushed apart. Once trained, you can give it any text labels and ask it to pick which label best matches a given... -
17
orjson
Fast, correct Python JSON library supporting dataclasses, datetimes
orjson is a fast, correct JSON library for Python. It benchmarks as the fastest Python library for JSON and is more correct than the standard json library or other third-party libraries. It serializes dataclass, datetime, numpy, and UUID instances natively. orjson supports CPython 3.8, 3.9, 3.10, 3.11, and 3.12. It distributes amd64/x86_64, aarch64/armv8, arm7, POWER/ppc64le, and s390x wheels for Linux, amd64 and aarch64 wheels for macOS, and amd64 and i686/x86 wheels for Windows. orjson does not support PyPy. ... -
18
Elm
Compiler for Elm, a functional language for reliable webapps
...Even on codebases with hundreds of thousands of lines of code, the compilation is done in a blink. Elm has its own virtual DOM implementation, designed for simplicity and speed. All values are immutable in Elm, and the benchmarks show that this helps us generate particularly fast JavaScript code. -
19
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. Designed to reason efficiently and decompose tasks like an experienced architect, M2.5 plans features, structure, and system design before... -
20
IQuest-Coder-V1 Model Family
New family of code large language models (LLMs)
...They support native long contexts up to 128K tokens, enabling them to reason across large codebases and multi-file interactions without context fragmentation, and include “Thinking” variants optimized for complex reasoning and “Loop” variants with recurrent mechanisms to improve inference efficiency. IQuest-Coder-V1 delivers state-of-the-art performance on multiple coding benchmarks, demonstrating strong results in competitive programming, tool use, and agentic code generation. -
21
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
...The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). While the internal architecture details are not fully documented publicly, the repo suggests that VL2 introduces enhancements over prior vision-language models (e.g. better scaling, cross-modal attention, more robust alignment) to improve grounding and multimodal understanding. -
22
Lapis
A web framework for Lua and OpenResty written in MoonScript
...With OpenResty, Lua is run directly inside of the Nginx worker using LuaJIT, giving you the smallest barrier between the webserver and your code. Have a look at Web Framework Benchmarks just to see how OpenResty stacks up against other platforms. Utilizing the power of Lua coroutines, you can write clean code that looks synchronous but can achieve high throughput by automatically running asynchronously without blocking. Networking operations like database queries and HTTP requests will automatically yield to allow for handling concurrent requests, all without all that callback spaghetti seen in other asynchronous platforms. -
23
Transfer Learning Repo
Transfer learning / domain adaptation / domain generalization
Transfer Learning Repo is an open-source repository that compiles resources, code implementations, and academic references related to transfer learning and its related research areas. The project functions as a large knowledge hub that organizes papers, tutorials, datasets, and software implementations across topics such as domain adaptation, domain generalization, multi-task learning, and few-shot learning. The repository includes surveys and theoretical explanations that help readers... -
24
LongBench
LongBench v2 and LongBench (ACL 25'&24')
LongBench is a comprehensive benchmark designed to evaluate the ability of large language models to understand and reason over very long textual contexts. Traditional language model benchmarks typically evaluate tasks involving relatively short inputs, which does not reflect many real-world applications such as analyzing large documents or entire code repositories. LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. The benchmark includes multiple categories such as single-document question answering, multi-document reasoning, summarization, long dialogue understanding, and code analysis. ... -
25
ReCall
Learning to Reason with Search for LLMs via Reinforcement Learning
ReCall is an open-source framework designed to train and evaluate language models that can reason through complex problems by interacting with external tools. The project builds on earlier work focused on teaching models how to search for information during reasoning tasks and extends that idea to a broader system where models can call a variety of external tools such as APIs, databases, or computation engines. Instead of relying purely on static knowledge stored inside the model, ReCall...
