	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 64.4%	5th 58.5%	- -	1st 64.4%	4th 60.8%	3rd 64.1%
63.4%	66%	56%		64%	59%	72%
47.8%	46%	25%		59%	53%	56%
51.2%	50%	44%		59%	48%	55%
63.8%	69%	58%		68%	58%	66%
79.8%	77%	87%		77%	80%	78%
72.8%	66%	73%		67%	81%	77%
67.0%	67%	63%		58%	75%	72%
46.2%	54%	27%		51%	48%	51%
63.2%	66%	63%		64%	70%	53%
57.4%	55%	58%		58%	58%	58%
54.6%	66%	31%		59%	58%	59%
63.4%	67%	55%		62%	68%	65%
63.0%	61%	64%		64%	52%	74%
57.6%	55%	55%		63%	61%	54%
58.6%	59%	55%		74%	41%	64%
60.2%	67%	56%		64%	47%	67%
79.4%	86%	94%		80%	63%	74%
61.4%	58%	65%		55%	71%	58%
45.0%	39%	51%		44%	34%	57%
64.6%	65%	58%		67%	71%	62%
46.2%	57%	24%		51%	52%	47%
55.4%	66%	25%		70%	50%	66%
56.8%	52%	69%		56%	35%	72%
63.4%	61%	64%		74%	54%	64%
57.8%	62%	57%		58%	58%	54%
52.6%	60%	43%		55%	54%	51%
60.2%	71%	74%		46%	53%	57%
66.0%	77%	70%		62%	59%	62%
60.0%	76%	53%		59%	66%	46%
81.2%	70%	97%		90%	80%	69%
59.6%	57%	66%		64%	45%	66%
86.0%	88%	95%		78%	91%	78%
54.2%	50%	44%		59%	59%	59%
69.6%	77%	43%		70%	85%	73%
53.0%	55%	37%		53%	64%	56%
66.2%	74%	62%		67%	64%	64%
74.8%	83%	75%		83%	59%	74%
79.4%	81%	77%		77%	77%	85%
54.8%	52%	53%		59%	59%	51%
72.8%	70%	63%		80%	71%	80%
74.0%	67%	75%		94%	67%	67%
62.4%	67%	50%		61%	61%	73%
58.4%	57%	62%		48%	55%	70%