	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 59.8%	2nd 60.5%	- -	3rd 59.8%	5th 54.4%	1st 60.5%
39.0%	38%	37%		42%	33%	45%
28.6%	29%	29%		20%	29%	36%
57.8%	67%	63%		51%	56%	52%
71.8%	72%	69%		68%	74%	76%
59.6%	56%	59%		54%	75%	54%
58.6%	52%	74%		52%	63%	52%
59.4%	56%	62%		67%	58%	54%
52.0%	55%	20%		60%	60%	65%
44.4%	43%	64%		34%	40%	41%
88.8%	83%	89%		86%	86%	100%
53.6%	76%	0%		75%	51%	66%
55.6%	54%	58%		56%	46%	64%
71.2%	78%	91%		77%	48%	62%
75.4%	74%	69%		73%	80%	81%
48.8%	43%	46%		41%	57%	57%
36.0%	30%	41%		41%	27%	41%
76.0%	81%	70%		70%	81%	78%
65.0%	66%	72%		56%	68%	63%
46.4%	50%	49%		52%	36%	45%
45.4%	50%	55%		52%	31%	39%
82.8%	83%	85%		87%	74%	85%
44.0%	55%	12%		43%	43%	67%
94.4%	98%	100%		89%	88%	97%
60.4%	56%	60%		59%	68%	59%
70.0%	79%	88%		76%	46%	61%
63.4%	60%	67%		69%	51%	70%
54.0%	63%	70%		41%	49%	47%
65.2%	65%	65%		65%	57%	74%
72.2%	80%	80%		80%	57%	64%
36.8%	32%	37%		37%	41%	37%
35.4%	30%	40%		40%	27%	40%
57.6%	59%	53%		61%	54%	61%
73.8%	65%	74%		77%	78%	75%
55.6%	52%	74%		51%	50%	51%
71.8%	77%	74%		74%	60%	74%
93.8%	92%	93%		96%	95%	93%
63.8%	56%	78%		60%	51%	74%
35.8%	37%	44%		38%	31%	29%
47.6%	50%	54%		59%	28%	47%
63.4%	69%	67%		63%	55%	63%
61.6%	68%	56%		55%	68%	61%
53.2%	48%	47%		71%	36%	64%
46.8%	49%	58%		47%	39%	41%
47.6%	46%	53%		55%	36%	48%
70.2%	69%	76%		70%	64%	72%
58.6%	58%	59%		62%	57%	57%