Test fixture
Arithmetic, symbolic steps, and structured problem solving.
The model receives the prompt (and optional system message). The run uses scorer exact_match with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.
What day comes after Monday? Answer with exactly: Tuesday
{
"expected": "Tuesday"
}temperature
0
max_tokens
12
timeout (s)
120
type
scored
file
reasoning_easy_15.json