Search Results for "benchmark" - Page 7
Sort By:
Showing 177 open source projects for "benchmark"
View related business solutions-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
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.
-
1
Netvlad
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD is a deep learning-based image descriptor framework developed by Relja Arandjelović for place recognition and image retrieval. It extends standard CNNs with a trainable VLAD (Vector of Locally Aggregated Descriptors) layer to create compact, robust global descriptors from image features. This implementation includes training code and pretrained models using the Pittsburgh and Tokyo datasets. -
2
Drug Extraction
Drug name extraction
...Using CONLL-Evaluation: processed 32065 tokens with 3656 phrases; found: 3251 phrases; correct: 2786. accuracy: 95.25%; precision: 85.70%; recall: 76.20%; FB1: 80.67 Using GATE Corpus Benchmark: Strict: P: 0.65 R: 0.73 F1: 0.69 Lenient: P: 0.74 R: 0.84 F1: 0.78 The details of how to reproduce evaluation, see README. To use standalone version for tagging download DrugExtractionStandalone.tar.gz from Files. -
3
Java Combinatorial Optimization Platform is used to solve combinatorial problems using common interface, providing means to easily add new algorithms and problems and to benchmark them.
-
4
tway
moved to https://github.com/sroycode/tway
Currently two way astar is implemented. For those interested I have uploaded a patch of this for pgrouting v1.05 moved to https://github.com/sroycode/tway -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
Clever Algorithms
Clever Algorithms: Nature-Inspired Programming Recipes
...The emphasis is on pragmatism—enough theory to understand why an algorithm works, and enough detail to get it running in your environment. It’s a useful starting point for students and practitioners who want to prototype, benchmark, or hybridize algorithms without digging through scattered academic papers. -
6
This program generates customizable hyper-surfaces (multi-dimensional input and output) and samples data from them to be used further as benchmark for response surface modeling tasks or optimization algorithms.
-
7
An IDE written in Java used to develop, visualize, test and benchmark evolutionary algorithms. The IDE is fully modular, allowing new algorithms to be added as plugins. It can be used to develop other algorithms as well.
-
8
The RTSCup is a programming environment for RTS games which can be used as a benchmark for evaluating several AI techniques. It is designed to make it easier and more intuitive for researchers to produce their applications over this plataform.
-
9
A test suite and benchmark for exact Euclidean distance transform algorithms used in Image Processing and computational geometry. It evaluates the exactness and speed of algorithms for a large number of test cases. Results can be visualized in Scilab.
-
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
10
OpenDiscreteDynamicProgrammingTemplate : founds optimal constrainted parameters of a discrete controls with second order optimization template replacing Hessian with directional derivatives and backpropagation for digital filter(as neural network)
-
11
GameBots is a research-oriented platform for building artificially-intelligent autonomous agents for computer games. It provides interfaces to sensing and acting in computer game environments and benchmark implementations of agents.
-
12
bge-small-en-v1.5
Compact English sentence embedding model for semantic search tasks
...It is compatible with popular libraries such as FlagEmbedding, Sentence-Transformers, and Hugging Face Transformers. The model achieves competitive results on the MTEB benchmark, especially in retrieval and classification tasks. With only 33.4M parameters, it provides a strong balance of accuracy and performance for English-only use cases. -
13
roberta-base
Robust BERT-based model for English with improved MLM training
...It captures contextual representations of language by masking 15% of input tokens and predicting them. RoBERTa is designed to be fine-tuned for a wide range of NLP tasks such as classification, QA, and sequence labeling, achieving strong performance on the GLUE benchmark and other downstream applications. -
14
translategemma-4b-it
Lightweight multimodal translation model for 55 languages
translategemma-4b-it is a lightweight, state-of-the-art open translation model from Google, built on the Gemma 3 family and optimized for high-quality multilingual translation across 55 languages. It supports both text-to-text translation and image-to-text extraction with translation, enabling workflows such as OCR-style translation of signs, documents, and screenshots. With a compact ~5B parameter footprint and BF16 support, the model is designed to run efficiently on laptops, desktops, and... -
15
Qwen3.6-35B-A3B
Open multimodal model for coding, agents, and long-context tasks
Qwen3.6-35B-A3B is an open-weight multimodal model built for real-world coding, agent workflows, and long-context reasoning. It combines a causal language model with a vision encoder, supports text, image, and video inputs, and is optimized for frameworks such as Transformers, vLLM, SGLang, and KTransformers. The model emphasizes stability, responsiveness, and practical developer productivity, with major improvements in agentic coding, frontend generation, and repository-level reasoning. A... -
16
Hermes 4
Hermes 4 FP8: hybrid reasoning Llama-3.1-405B model by Nous Research
Hermes 4 405B FP8 is a cutting-edge large language model developed by Nous Research, built on Llama-3.1-405B and optimized for frontier reasoning and alignment. It introduces a hybrid reasoning mode with explicit <think> segments, enabling the model to deliberate deeply when needed and switch to faster responses when desired. Post-training improvements include a vastly expanded corpus with ~60B tokens, boosting performance across math, code, STEM, logic, creativity, and structured outputs.... -
17
GLM-4.5-Air
Compact hybrid reasoning language model for intelligent responses
GLM-4.5-Air is a multilingual large language model with 106 billion total parameters and 12 billion active parameters, designed for conversational AI and intelligent agents. It is part of the GLM-4.5 family developed by Zhipu AI, offering hybrid reasoning capabilities via two modes: a thinking mode for complex reasoning and tool use, and a non-thinking mode for immediate responses. The model is optimized for efficiency and deployment, delivering strong results across 12 industry benchmarks,... -
18
bge-large-en-v1.5
BGE-Large v1.5: High-accuracy English embedding model for retrieval
...It uses a BERT-based architecture fine-tuned to produce high-quality dense vector representations optimized for sentence similarity, search, and retrieval. This model is part of the BGE (BAAI General Embedding) family and delivers improved similarity distribution and state-of-the-art results on the MTEB benchmark. It is recommended for use in document retrieval tasks, semantic search, and passage reranking, particularly when paired with a reranker like BGE-Reranker. The model supports inference through multiple frameworks, including FlagEmbedding, Sentence-Transformers, LangChain, and Hugging Face Transformers. It accepts English text as input and returns normalized 1024-dimensional embeddings suitable for cosine similarity comparisons. -
19
Gemma 4 12B
Unified multimodal Gemma model for local coding and reasoning
...The model has 11.95B parameters, 48 layers, a 256K-token context window, and support for over 140 languages. It also includes configurable thinking modes, native system prompt support, function calling, and strong benchmark performance for its size. It is optimized for consumer GPUs, workstations, and streamlined local deployment. -
20
Command A+
4-bit Command A+ model for enterprise agents and multilingual tasks
...The W4A4 release applies 4-bit weight and activation quantization mainly to MoE experts, preserving attention components at full precision to reduce quality loss while improving speed, latency, and hardware efficiency. Cohere recommends W4A4 for most users because it offers a smaller hardware footprint with negligible benchmark differences compared to BF16 and FP8 versions. The model supports a 128K input context and 64K output length, covers 48 languages, and includes conversational tool-use capabilities with JSON-schema tools and optional citation grounding. -
21
DeepSeek-V4-Flash
Efficient MoE model for million-token reasoning and coding
DeepSeek-V4-Flash is a preview Mixture-of-Experts language model built for efficient million-token context intelligence. It has 284B total parameters with 13B activated and supports a 1M-token context window, making it suitable for long-document reasoning, complex coding, agentic workflows, and large-scale information processing. The model uses a hybrid attention architecture that combines Compressed Sparse Attention and Heavily Compressed Attention to improve long-context efficiency, while... -
22
GigaChat 3 Ultra
High-performance MoE model with MLA, MTP, and multilingual reasoning
GigaChat 3 Ultra is a flagship instruct-model built on a custom Mixture-of-Experts architecture with 702B total and 36B active parameters. It leverages Multi-head Latent Attention to compress the KV cache into latent vectors, dramatically reducing memory demand and improving inference speed at scale. The model also employs Multi-Token Prediction, enabling multi-step token generation in a single pass for up to 40% faster output through speculative and parallel decoding techniques. Its... -
23
DeepSeek-V3.2-Speciale
High-compute ultra-reasoning model surpassing model surpassing GPT-5
...DeepSeek-V3.2-Speciale contributed to gold-medal solutions in the 2025 IMO, IOI, ICPC World Finals, and CMO, demonstrating its ability to handle elite-level problem solving. It is released under the MIT license and includes curated benchmark solutions for community verification and analysis. -
24
DeepSeek-V3.1-Terminus
685B model with improved agents and consistency
DeepSeek-V3.1-Terminus is an updated release in the DeepSeek-V3.1 series, maintaining the original model’s large-scale reasoning and generative capabilities while addressing several key user-reported issues. It improves language consistency, reducing mixed Chinese-English outputs and eliminating abnormal characters, enhancing reliability in multilingual scenarios. The update also refines agentic capabilities, especially for the Code Agent and Search Agent, leading to better tool integration... -
25
Qwen3-Next
Qwen3-Next: 80B instruct LLM with ultra-long context up to 1M tokens
Qwen3-Next-80B-A3B-Instruct is the flagship release in the Qwen3-Next series, designed as a next-generation foundation model for ultra-long context and efficient reasoning. With 80B total parameters and 3B activated at a time, it leverages hybrid attention (Gated DeltaNet + Gated Attention) and a high-sparsity Mixture-of-Experts architecture to achieve exceptional efficiency. The model natively supports a context length of 262K tokens and can be extended up to 1 million tokens using RoPE...
