Registry / all records
315 research AI agents · live GitHub metrics · community reviews
Retired projects →harbor-framework/harbor
Framework for evaluating and improving agents
SWE-bench/SWE-bench
SWE-bench: Can Language Models Resolve Real-world Github Issues?
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
sierra-research/tau2-bench
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
openai/mle-bench
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
centerforaisafety/hle
Humanity's Last Exam
pinchbench/skill
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
openai/frontier-evals
OpenAI Frontier Evals
TIGER-AI-Lab/ClawBench
Open-source benchmark for browser AI agents on daily tasks.
claw-eval/claw-eval
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
Ayanami0730/deep_research_bench
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
idavidrein/gpqa
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
hkust-nlp/Toolathlon
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
harbor-framework/terminal-bench-2
No description yet — run the GitHub refresh to fetch one.
ktwu01/benchmark-radar
Track 50,331+ AI benchmark, eval, dataset, and data-quality records from 41 public sources, with linked evidence and daily updates.
InternScience/ResearchClawBench
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
scicode-bench/SciCode
A benchmark that challenges language models to code solutions for scientific problems
SuperGPQA/SuperGPQA
No description yet — run the GitHub refresh to fetch one.
OSU-NLP-Group/ScienceAgentBench
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
Future-House/BixBench
Benchmark for LLM-based Agents in Computational Biology
evolvent-ai/ClawMark
🦞 ClawMark: A Living-World Benchmark for Multi-Day, Multimodal Coworker Agents
gersteinlab/MedicalAgentsBench
[Patterns] MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
microsoft/HealthAgentBench
No description yet — run the GitHub refresh to fetch one.
AutoMedBench/AutoMedBench
MedAutoBench — Medical AutoResearch Benchmark for Autonomous AI Agents
zhao-zy15/RareArena
A Comprehensive Rare Disease Diagnostic Dataset with nearly 50,000 patients covering more than 4000 diseases
darlednik/GENEB
GENEB: ICML 2026 benchmark for genomic foundation models across 100 tasks and 13 functional categories.