meta-harness-tbench2-artifact is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named meta-harness-tbench2-artifact among their alternatives. The relationship is not symmetric — how meta-harness-tbench2-artifact rates them is a separate judgement, made when meta-harness-tbench2-artifact is analysed in its own right.
calls meta-harness-tbench2-artifact “choose if you want a research harness targeting Terminal-Bench 2.0 instead of SWE-bench.”
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]