Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Paper
•
2601.11868
•
Published
•
28
dylu
ludybupt
AI & ML interests
None yet
Recent Activity
authored
a paper
about 8 hours ago
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
new activity
about 2 months ago
Qwen/Qwen3-Next-80B-A3B-Thinking:Request for SWE-bench-Verified Evaluation Metrics of Qwen3-Next-80B-A3B.
new activity
4 months ago
SWE-bench/SWE-smith:How to get Previous version images(May 8 version in docker hub)
Organizations
None yet
authored
a
paper
about 8 hours ago