CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Open paper
Benchmark
Model
Rank
Results
agents-on-bfclv4
CLI-Universe-32B
–
Accuracy: 58.0
code-generation-on-terminal-bench-2-0-terminus-2
CLI-Universe-32B (Terminus 2)
–
Accuracy: 33.4
Rank counts only results with a code link.