Search Results for "benchmark"
Sort By:
Showing 192 open source projects for "benchmark"
View related business solutions-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
1
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
...Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. GLM-4.6 also enhances writing quality, producing outputs that better align with human preferences and role-playing scenarios. Benchmark evaluations demonstrate that it not only outperforms GLM-4.5 but also rivals leading global models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4. -
2
BEIR
A Heterogeneous Benchmark for Information Retrieval
BEIR is a benchmark framework for evaluating information retrieval models across various datasets and tasks, including document ranking and question answering. -
3
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
AgentBench is an open-source benchmark designed to evaluate the capabilities of large language models when used as autonomous agents. Unlike traditional language model benchmarks that focus on static text tasks, AgentBench measures how models perform in interactive environments that require planning, reasoning, and decision-making. The benchmark includes multiple environments that simulate realistic scenarios such as web interaction, database querying, and problem solving tasks. ... -
4
LongBench
LongBench v2 and LongBench (ACL 25'&24')
...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. It supports bilingual evaluation in English and Chinese to assess multilingual capabilities across extended contexts. Newer versions of the benchmark introduce extremely long context windows ranging from thousands to millions of tokens, enabling researchers to test the limits of modern long-context models. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
AICGSecEval
A.S.E (AICGSecEval) is a repository-level AI-generated code security
AICGSecEval is an open-source benchmark framework designed to evaluate the security of code generated by artificial intelligence systems. The project was developed to address concerns that AI-assisted programming tools may produce insecure code containing vulnerabilities such as injection flaws or unsafe logic. The framework constructs evaluation tasks based on real-world software repositories and known vulnerability cases derived from CVE records. -
6
HumanEval
Code for the paper "Evaluating Large Language Models Trained on Code"
...The benchmark has become a standard for evaluating code generation models, including those in the Codex and GPT families. Researchers can use the dataset to run reproducible comparisons across models and track improvements in functional code synthesis. By focusing on correctness through execution, human-eval provides a rigorous and practical way to evaluate programming capabilities in AI systems. -
7
DeepSeek-OCR 2
Visual Causal Flow
...It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. The repository provides model code and inference scripts that let researchers and developers run and benchmark the system on both images and PDFs, with support for batch evaluation and optimized pipelines leveraging vLLM and transformers. -
8
Meta Agents Research Environments (ARE)
Meta Agents Research Environments is a comprehensive platform
...Unlike static benchmarks, ARE supports environments where agents must adapt to changes over time and reason over sequences of actions. It interacts with applications and faces uncertainty. The included Gaia2 benchmark offers 800 scenarios across multiple “universes”. It can test reasoning, memory, tool use, and adaptability. Integration with simulated applications/agent APIs (email, file system, etc.). Support for multiple AI model backends/providers. -
9
SAM 3
Code for running inference and finetuning with SAM 3 model
...This capability is grounded in a new data engine that automatically annotated over four million unique concepts, producing a massive open-vocabulary segmentation dataset and enabling the model to achieve 75–80% of human performance on the SA-CO benchmark, which itself spans 270K unique concepts. -
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
10
MTEB
MTEB: Massive Text Embedding Benchmark
...This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks. This suggests that the field has yet to converge on a universal text embedding method and scale it up sufficiently to provide state-of-the-art results on all embedding tasks. -
11
SDGym
Benchmarking synthetic data generation methods
The Synthetic Data Gym (SDGym) is a benchmarking framework for modeling and generating synthetic data. Measure performance and memory usage across different synthetic data modeling techniques – classical statistics, deep learning and more! The SDGym library integrates with the Synthetic Data Vault ecosystem. You can use any of its synthesizers, datasets or metrics for benchmarking. You also customize the process to include your own work. Select any of the publicly available datasets from the... -
12
Hallucination Leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations
...By focusing on hallucination rates rather than traditional metrics such as accuracy or fluency, the benchmark highlights an important aspect of AI system safety and trustworthiness. The leaderboard is regularly updated as new models are released and evaluation methods evolve. -
13
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
...Developed with MindSpore and later made PyTorch-compatible, it is capable of multilingual code generation, cross-lingual code translation, code completion, summarization, and explanation. It has been benchmarked on HumanEval-X, a multilingual program synthesis benchmark introduced alongside the model, and achieves state-of-the-art performance compared to other open models like InCoder and CodeGen. CodeGeeX also powers IDE plugins for VS Code and JetBrains, offering features like code completion, translation, debugging, and annotation. The model supports Ascend 910 and NVIDIA GPUs, with optimizations like quantization and FasterTransformer acceleration for faster inference. -
14
SIA
AI framework to autonomously improve the performance of any AI system
SIA is a self-improving AI framework designed to improve the performance of models or agents on benchmark tasks. It uses an iterative loop where a meta-agent creates or updates a task-specific target agent, while a feedback agent studies results and proposes improvements. The framework can refine both the harness around the task and the agent implementation itself. It is aimed at research and experimentation across tasks such as machine learning benchmarks, legal classification, code optimization, and scientific workflows. ... -
15
AutoAgent AI
Autonomous harness engineering
...Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. It runs inside Docker for safe execution and reproducibility. This approach shifts agent development from manual design to automated optimization. ... -
16
PyTorch Geometric
Geometric deep learning extension library for PyTorch
It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers. In addition, it consists of an easy-to-use mini-batch loader for many small and single giant graphs, a large number of common benchmark datasets (based on simple interfaces to create your own), and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds. We have outsourced a lot of functionality of PyTorch Geometric to other packages, which needs to be additionally installed. These packages come with their own CPU and GPU kernel implementations based on C++/CUDA extensions. ... -
17
Recursive Language Models
General plug-and-play inference library for Recursive Language Models
...Within the framework, you can define custom agents, environments, policy networks, and reward structures while leveraging built-in dataset utilities, logging, and checkpointing for reproducible experiments. RLM also includes integration with popular simulation environments and benchmark suites, giving researchers a ready-made playground for algorithm comparison and performance tracking. -
18
D4RL
Collection of reference environments, offline reinforcement learning
D4RL (Datasets for Deep Data-Driven Reinforcement Learning) is a benchmark suite focused on offline reinforcement learning — i.e., learning policies from fixed datasets rather than via online interaction with the environment. It contains standardized environments, tasks and datasets (observations, actions, rewards, terminals) aimed at enabling reproducible research in offline RL. Researchers can load a dataset for a given task (e.g., maze navigation, manipulation) and apply their algorithm without the need to collect fresh transitions, which accelerates experimentation and comparison. ... -
19
Behaviour Suite Reinforcement Learning
bsuite is a collection of carefully-designed experiments
...Its main goal is to identify, measure, and analyze fundamental aspects of learning efficiency and generalization in RL algorithms. The library enables researchers to benchmark their agents on standardized tasks, facilitating reproducible and transparent comparisons across different approaches. Each experiment in bsuite is meticulously designed to capture key challenges in RL, such as exploration, credit assignment, and stability. The framework supports automated logging and analysis, generating standardized output compatible with Jupyter notebooks for streamlined evaluation. ... -
20
Open Source Vizier
Python-based research interface for blackbox
...Defines abstractions and utilities for implementing new optimization algorithms for research and to be hosted in the service. A wide collection of objective functions and methods to benchmark and compare algorithms. Define a problem statement and study configuration. Setup a local server, setup a client to connect to the server, perform a typical tuning loop, and use other client APIs. -
21
Meta-World
Collections of robotics environments
Meta-World is an open-source benchmark suite of robotic manipulation environments focused on multi-task and meta reinforcement learning. It provides a large collection of continuous-control tasks, such as reaching, pushing, opening doors, and manipulating objects with a simulated robot arm. The library defines standardized benchmarks like MT1, MT10, and MT50 for multi-task learning, where a single policy is trained across different numbers of tasks. -
22
Qwen3 Embedding
Designed for text embedding and ranking tasks
...It builds upon the Qwen3 base/dense models and offers several sizes (0.6B, 4B, 8B parameters), for both embedding and reranking, with high multilingual capability, long‐context understanding, and reasoning. It achieves state-of-the-art performance on benchmarks like MTEB (Multilingual Text Embedding Benchmark) and supports instruction-aware embedding (i.e. embedding task instructions along with queries) and flexible embedding/vector dimension definitions. It is meant for tasks such as text retrieval, classification, clustering, bitext mining, and code retrieval. -
23
LLM Colosseum
Benchmark LLMs by fighting in Street Fighter 3
LLM-Colosseum is an experimental benchmarking framework designed to evaluate the capabilities of large language models through gameplay interactions rather than traditional text-based benchmarks. The system places language models inside the environment of the classic video game Street Fighter III, where they must interpret the game state and decide which actions to perform during combat. This setup creates a dynamic environment that tests reasoning, situational awareness, and decision-making... -
24
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile. -
25
openbench
Provider-agnostic, open-source evaluation infrastructure
...It bundles dozens of evaluation suites — covering knowledge, reasoning, math, code, science, reading comprehension, long-context recall, graph reasoning, and more — so users don’t need to assemble disparate datasets themselves. With a simple CLI interface (e.g. bench eval <benchmark> --model <model-id>), you can quickly evaluate any model supported by Groq or other providers (OpenAI, Anthropic, HuggingFace, local models, etc.). openbench also supports private/local evaluations: you can integrate your own custom benchmarks or data (e.g. internal test suites, domain-specific tasks) to evaluate models in a privacy-preserving way.
