Test fixture
Roblox OpenGameEval tasks. Special category: visible in breakdowns, excluded from Overall.
The model receives the prompt (and optional system message). The run uses scorer roblox_open_eval with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.
[Roblox OpenGameEval] Make people keep bouncing when they are on the trampoline.
{
"input_script": "[embedded in CLI runner]",
"upstream_path": "Evals/052_surburban_trampoline_bounce.lua",
"upstream_sha256": "863097a7a92487c5c7a7764394d4a9a8759cf2e96bc982be2aed5850d33b367b",
"scenario_name": "052_surburban_trampoline_bounce",
"place": "surburban.rbxl",
"eval_kind": "codegen"
}temperature
0
max_tokens
1
timeout (s)
900
type
scored
file
052_surburban_trampoline_bounce.json