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 the nitro effect color the same color as the car.
{
"input_script": "[embedded in CLI runner]",
"upstream_path": "Evals/095_racing_nitro_effect_color.lua",
"upstream_sha256": "a8898a067e13b5728ac52ffe0a18bb2774de196e4abf63daa7982ce70eba66f0",
"scenario_name": "pilot_030",
"place": "racing.rbxl",
"eval_kind": "codegen"
}temperature
0
max_tokens
1
timeout (s)
900
type
scored
file
095_racing_nitro_effect_color.json