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 it so that when a player is driving a car and jumps, the car jumps
{
"input_script": "[embedded in CLI runner]",
"upstream_path": "Evals/086_racing_car_jump.lua",
"upstream_sha256": "e2c5f2cc0299c7fb801cafd49dca18f695123fc7cd758e0093ac9a071649b796",
"scenario_name": "086_racing_car_jump",
"place": "racing.rbxl",
"eval_kind": "codegen"
}temperature
0
max_tokens
1
timeout (s)
900
type
scored
file
086_racing_car_jump.json