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] {"role":"user","content":"Make the items cheese burger and water bottle spawn in various places around the map.
Include a hunger, thirst, and stamina bar; make these bars visible.
Make it so when the player presses "Q," they perform a forward dash with a cooldown of 30 seconds.
Make the cheese burger restore half of the hunger bar and the water bottle restore half of the thirst bar."}{
"input_script": "[embedded in CLI runner]",
"upstream_path": "Evals/120_food_spawn_hunger_bar.lua",
"upstream_sha256": "a1e16150718cd6335501834c5041ac5d2e236eb40ff321b3ffd03d299372b1d9",
"scenario_name": "120_food_spawn_hunger_bar",
"place": "baseplate.rbxl",
"eval_kind": "codegen"
}temperature
0
max_tokens
1
timeout (s)
900
type
scored
file
120_food_spawn_hunger_bar.json