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.
Find the next number in the sequence: 3, 6, 12, 24, 48, ?. Return only the number.
{
"expected": "96"
}temperature
0
max_tokens
20
timeout (s)
120
type
scored
file
reasoning_medium_04.json