Collection of evals for Inspect AI
Appears on
Quick read
Latest capture 2026-09-09 03:07
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
52 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Claude Code 48
Devin 3
28 more paths detected.
7 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +151
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Open-source benchmark for browser AI agents on daily tasks.
The LLM Evaluation Framework
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
An agent benchmark with tasks in a simulated software company.
SWE-bench: Can Language Models Resolve Real-world Github Issues?
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
