Files
Terminus-Qwen3-8b/.eval_results/terminal_bench_2.yaml

9 lines
238 B
YAML
Raw Normal View History

- dataset:
id: harborframework/terminal-bench-2.0
task_id: terminalbench_2
value: 4.9
source:
url: https://huggingface.co/OrionLLM/Terminus-Qwen3-8b
name: Model card
user: DedeProGames
notes: "agent: Terminus 2"