	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 47.4%	3rd 42.6%	6th 36.6%	5th 36.7%	4th 37.1%	2nd 45.6%
91.3%	88%	95%	100%	97%	91%	77%
92.5%	88%	99%	97%	97%	97%	77%
2.5%	0%	0%	1%	0%	0%	14%
78.3%	32%	99%	97%	97%	90%	55%
43.5%	66%	54%	58%	73%	2%	8%
16.3%	0%	0%	0%	0%	9%	89%
25.3%	43%	0%	35%	0%	9%	65%
85.3%	88%	87%	97%	97%	88%	55%
79.7%	88%	87%	97%	91%	64%	51%
2.3%	0%	0%	0%	0%	0%	14%
54.8%	84%	0%	81%	0%	78%	86%
96.0%	99%	88%	100%	97%	97%	95%
16.5%	20%	78%	1%	0%	0%	0%
62.5%	88%	32%	81%	0%	87%	87%
27.2%	0%	68%	0%	95%	0%	0%
46.3%	95%	0%	0%	88%	0%	95%
30.7%	26%	16%	0%	88%	54%	0%
0.0%	0%	0%	0%	0%	0%	0%
58.5%	91%	6%	81%	0%	87%	86%
92.7%	90%	88%	100%	97%	86%	95%
59.8%	84%	88%	0%	24%	86%	77%
72.7%	35%	87%	58%	88%	91%	77%
42.3%	0%	78%	91%	0%	85%	0%
72.0%	93%	88%	0%	88%	86%	77%
6.0%	0%	0%	36%	0%	0%	0%
36.5%	66%	52%	1%	0%	22%	78%
22.8%	2%	31%	71%	0%	8%	25%
23.2%	72%	0%	0%	59%	0%	8%
59.0%	15%	87%	83%	7%	88%	74%
58.5%	16%	78%	81%	16%	86%	74%
79.7%	78%	78%	97%	87%	88%	50%
6.2%	9%	0%	28%	0%	0%	0%
26.0%	66%	0%	1%	0%	0%	89%
9.2%	24%	0%	0%	0%	0%	31%
12.5%	32%	32%	0%	3%	0%	8%
28.8%	66%	0%	1%	14%	14%	78%
42.0%	67%	54%	58%	7%	14%	52%
27.7%	0%	78%	0%	88%	0%	0%
3.2%	9%	0%	0%	0%	0%	10%
17.0%	66%	0%	1%	0%	0%	35%
0.0%	0%	0%	0%	0%	0%	0%
89.7%	87%	88%	97%	97%	91%	78%
34.7%	66%	52%	1%	0%	0%	89%
3.3%	0%	0%	0%	0%	0%	20%
37.2%	71%	68%	0%	84%	0%	0%
29.0%	84%	0%	1%	0%	0%	89%
34.5%	60%	54%	0%	0%	68%	25%
25.7%	30%	51%	1%	64%	0%	8%
0.0%	0%	0%	0%	0%	0%	0%
87.8%	84%	87%	97%	91%	91%	77%