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] Turn the lights on/off based on time of day
{
"input_script": "[embedded in CLI runner]",
"upstream_path": "Evals/103_city_lights_on_off.lua",
"upstream_sha256": "cd3b33f9d988822c0d2ea32459769b7308fa21e5ddb1990affaa6bd0c8701c7b",
"scenario_name": "103_city_lights_on_off",
"place": "modern_city.rbxl",
"eval_kind": "codegen"
}temperature
0
max_tokens
1
timeout (s)
900
type
scored
file
103_city_lights_on_off.json