	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 47.9%	3rd 43.0%	6th 36.6%	5th 38.2%	4th 38.7%	2nd 46.2%
93.2%	92%	99%	100%	97%	94%	77%
92.3%	93%	99%	97%	97%	91%	77%
4.5%	12%	0%	1%	0%	0%	14%
88.8%	80%	99%	97%	97%	86%	74%
41.3%	52%	54%	58%	65%	11%	8%
19.5%	20%	7%	1%	0%	0%	89%
34.2%	77%	7%	35%	7%	15%	64%
86.0%	92%	87%	97%	97%	88%	55%
80.2%	84%	87%	97%	91%	71%	51%
2.3%	0%	0%	0%	0%	0%	14%
59.7%	97%	6%	81%	0%	88%	86%
96.0%	97%	88%	100%	97%	97%	97%
13.0%	77%	0%	1%	0%	0%	0%
54.8%	7%	78%	81%	0%	88%	75%
39.0%	74%	68%	0%	92%	0%	0%
58.0%	95%	56%	0%	88%	14%	95%
35.0%	0%	54%	0%	88%	68%	0%
0.0%	0%	0%	0%	0%	0%	0%
61.3%	99%	14%	81%	0%	88%	86%
96.0%	97%	99%	100%	97%	86%	97%
52.0%	35%	78%	0%	24%	88%	87%
82.3%	84%	87%	58%	88%	91%	86%
41.8%	7%	78%	81%	0%	85%	0%
72.0%	93%	88%	0%	91%	86%	74%
2.7%	4%	0%	12%	0%	0%	0%
23.7%	0%	52%	1%	0%	0%	89%
24.5%	5%	31%	71%	0%	8%	32%
14.5%	20%	0%	0%	59%	0%	8%
60.2%	15%	78%	83%	20%	88%	77%
66.3%	62%	78%	81%	16%	87%	74%
80.2%	73%	78%	97%	87%	88%	58%
6.2%	9%	0%	28%	0%	0%	0%
29.2%	71%	0%	1%	0%	14%	89%
18.0%	66%	0%	35%	0%	0%	7%
6.2%	8%	15%	0%	6%	0%	8%
26.3%	65%	0%	1%	0%	14%	78%
49.3%	66%	54%	58%	66%	0%	52%
42.2%	0%	78%	0%	87%	88%	0%
3.2%	9%	0%	0%	0%	0%	10%
15.0%	59%	0%	0%	0%	0%	31%
0.0%	0%	0%	0%	0%	0%	0%
88.0%	72%	88%	97%	97%	97%	77%
33.5%	59%	52%	1%	0%	0%	89%
1.2%	0%	0%	0%	0%	0%	7%
39.3%	84%	68%	0%	84%	0%	0%
29.7%	66%	0%	1%	0%	22%	89%
18.3%	16%	54%	0%	15%	0%	25%
18.5%	2%	14%	0%	64%	6%	25%
2.0%	12%	0%	0%	0%	0%	0%
86.2%	88%	78%	97%	91%	86%	77%