Havuz

🔥 Orbia: Do Generated Videos Form a Consistent 3D World?

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

JevGym is an open-source platform designed to benchmark and facilitate better probabilistic estimation in Jev-alike models

HistorianRCA: a root cause analysis benchmark. 90 days of simulated plant historian data from a steam-heated hold tank, with hidden faults t

MathPinpoint: problem-level math retrieval dataset. Find the web page that solves the same problem under the same conditions, correctly. 3.5

[Public preview] Hard human-written reasoning puzzles: 749 answered items in 15 topics (707 scored core), with protocol and scorer.

A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.

Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.

[Public preview] The first public quant trading benchmark scored against what professional traders actually made on the same asset

MathmoBench, kombinatoryal matematik sorularında modelleri makineyle doğrulanabilir çözüm ve imkânsızlık kanıtları üzerinden değerlendiren bir benchmark ve doğrulama aracıdır.

Neden yükseliyor · AI evaluation odağı ve sertifika tabanlı, deterministik puanlama yaklaşımı dikkat çekebilir. Dört günlük repo için 85 yıldız erken ilgi gösteriyor; ancak 2 commit ve 1 farklı yazar, benimseme veya sürdürülebilirlik kanıtı değil.

An esoteric programming language built to break LLMs and coding agents.

PaperBench High-Difficulty and Expanded Tasks: paper reproduction beyond machine learning. 93 tasks in 12 research areas, run in domain-nati

Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

MerchantBench is a 365-day, order-level benchmark for evaluating the long-term coherence of LLM agents in seller-side e-commerce operations.

dsh-model-master（模型选择大师）— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to mea

DiagSafe: diagnostic LLM safety benchmark with prompt-level rubrics (3,489 bilingual prompts, 84-label taxonomy)

Can coding agents build the agent you actually want? A benchmark of 25 agent software engineering tasks across creation, editing and optimiz

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

Official code for InfoVis: one 9B model for slide image generation and editing, with the VisSlideBench benchmark and 15M+ training records.

Reproducible benchmark that compares VictoriaLogs, Loki, Elasticsearch, OpenSearch, SigNoz and ClickStack

[ICML 2026] Autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.

Benchmarking coding agents on formalized undergraduate research problems

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its

ReviewBench is an open, reproducible benchmark for evaluating AI code review systems on real-world pull requests.

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.

Рейтинг VPS-хостингов по тестам сообщества: что взять под ноду, мост или бота

Benchmark and controlled study of LLM-based novelty judges for research ideas. Code and data for "Old Ideas, Novel Problems" (arXiv 2610.020

Best Open Source Aim Trainer Benchmark Tool 2026

A counterfactual battery for instruction following in vision-language-action policies: change one word of the instruction, hold the scene, a

Aim Genetics Lab Open Research Tools 2026: Build Precision Breeding Models

aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastru

Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

The Virtual Filesystem Interface for AI Agents

Benchmark aberto de LLMs para o processo legislativo brasileiro

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public

[EMNLP 2026] WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

DolphinBench - Mapping the Pareto frontier of Agent Memory

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

A Benchmark for Retrieving Papers that Inspire New Research

Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

A benchmark for testing whether coding agents can resolve engineering tasks in scientific software

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.

Measurement harness for proxy providers, browser engines and scraping targets. Every claim carries the run it came from.

glTF 2.0 versions of common graphics research scenes