	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 57.2%	2nd 55.5%	- -	3rd 54.9%	5th 54.0%	4th 54.2%
50.8%	67%	43%		50%	51%	43%
66.6%	62%	62%		72%	62%	75%
75.0%	79%	85%		75%	65%	71%
53.0%	49%	48%		57%	53%	58%
38.6%	42%	25%		29%	43%	54%
33.8%	31%	27%		36%	43%	32%
75.6%	76%	71%		77%	77%	77%
49.0%	69%	37%		44%	51%	44%
75.0%	77%	76%		76%	73%	73%
52.4%	54%	54%		50%	55%	49%
46.8%	45%	44%		45%	46%	54%
70.2%	64%	68%		68%	75%	76%
48.6%	61%	72%		51%	22%	37%
54.6%	56%	50%		56%	54%	57%
50.0%	55%	42%		48%	55%	50%
66.0%	64%	68%		72%	61%	65%
53.0%	57%	54%		54%	55%	45%
61.0%	63%	69%		65%	53%	55%
41.0%	43%	50%		42%	28%	42%
66.2%	68%	68%		63%	69%	63%
60.0%	60%	60%		58%	60%	62%
51.4%	59%	54%		50%	47%	47%
67.4%	71%	68%		58%	81%	59%
48.8%	46%	52%		41%	52%	53%
50.4%	54%	53%		44%	50%	51%
82.0%	90%	82%		83%	72%	83%
56.6%	58%	60%		58%	57%	50%
48.6%	49%	51%		51%	50%	42%
57.2%	60%	57%		55%	56%	58%
45.2%	49%	47%		40%	39%	51%
65.2%	66%	51%		72%	75%	62%
29.4%	30%	21%		32%	32%	32%
51.6%	52%	55%		48%	55%	48%
58.0%	64%	57%		57%	50%	62%
32.0%	30%	37%		30%	33%	30%
58.4%	54%	62%		58%	59%	59%
70.2%	70%	69%		69%	69%	74%
28.4%	29%	23%		27%	37%	26%
46.0%	46%	49%		43%	44%	48%
58.8%	55%	65%		59%	59%	56%
48.8%	48%	46%		46%	54%	50%
55.4%	55%	63%		51%	59%	49%
34.6%	30%	43%		38%	31%	31%
36.6%	51%	28%		47%	24%	33%
68.4%	68%	73%		65%	71%	65%
64.4%	61%	68%		68%	61%	64%
37.6%	40%	28%		49%	31%	40%
60.4%	67%	59%		63%	59%	54%
53.0%	64%	60%		47%	50%	44%
67.2%	70%	82%		70%	48%	66%
62.8%	62%	70%		62%	55%	65%
66.6%	69%	67%		70%	66%	61%
80.2%	74%	77%		77%	90%	83%
49.8%	54%	48%		47%	50%	50%