AgentDish directory

swe-bench

Accepted listings with this tag.

Listing Category Score Trend Checked
#492 ↑ +2
OptiQ Code

A terminal coding agent for Mac that runs on local models through MLX, edits code, runs tests, and keeps everything on-device.

Developer Tools / AI Coding Assistant 86 ↑ +2 44 days ago Details
#1271 ↓ -2
clawmark

A local Rust CLI for A/B testing two CLAUDE.md files against a fixed SWE-bench Lite smoke set, with doctor, run, and report commands.

Developer Tools / AI Benchmarking 82 ↓ -2 74 days ago Details