An in-the-wild benchmark for AI agents in the production harness.
Appears on
Quick read
Latest capture 2026-09-07 03:08
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.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
7 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +109
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
A benchmark for LLMs on complicated tasks in the terminal
Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
Open, reproducible benchmarks for crypto infrastructure: aggregators, bridges, blockchains, perps. Live data, public methodology.
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Open-source benchmark for browser AI agents on daily tasks.
