Infron · Motif 3 · 46문항 × 3회 · Python TAR. 131,072 output tokens · 기본 1,800초 · 6+1 turns. ACC는 전체 138회, Pass@1은 각 문항의 첫 유효 시도, Pass@3는 3회 내 정답으로 계산합니다.
Problem Statement
, 이고 인 삼각형 ABC의 넓이를 구하시오.
최종 정수 답을 안에 쓰세요.
Ground Truth
12
Recorded model response / solution
Reasoning Process
Recorded Python call:
import math
AB=5
AC=6
cosA=-3/5
sinA=math.sqrt(1-cosA**2)
area=0.5*AB*AC*sinA
area
Tool Output
Execution succeeded
Reasoning Process
Recorded Python call:
import math
AB=5; AC=6; cosA=-3/5
sinA=math.sqrt(1-cosA**2)
area=0.5*AB*AC*sinA
print(sinA, area)
Tool Output
Execution succeeded
0.8 12.0
Reasoning Process
삼각형 의 넓이는
따라서 삼각형 의 넓이는
Final Model Output
12
Comparative Analysis (Pcommon_18) (Average across runs)
Averages use reported measurements only. Missing usage is not treated as zero.
Avg Time Taken
Union Alpha
96.0
Solar Pro 4
28.7
Grok 4.7
10.9
MiMo V2.6 Pro
8.5
Motif 3
7.8
Muse Spark 1.3
5.6
DeepSeek V4.1 Flash
4.1
Solar Mini 4 Preview
1.5
Avg Token Usage
Grok 4.7
6,949
Solar Pro 4
3,872
Muse Spark 1.3
3,192
Union Alpha
2,841
Motif 3
2,286
DeepSeek V4.1 Flash
2,236
Solar Mini 4 Preview
1,800
MiMo V2.6 Pro
976