	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 63.1%	3rd 61.2%	- -	4th 59.6%	2nd 62.6%	5th 55.7%
52.2%	67%	55%		47%	53%	39%
64.6%	66%	61%		68%	74%	54%
93.2%	92%	92%		94%	100%	88%
59.6%	63%	45%		62%	68%	60%
57.4%	62%	44%		50%	66%	65%
66.0%	55%	61%		71%	87%	56%
67.6%	75%	70%		63%	73%	57%
48.4%	72%	44%		37%	59%	30%
51.0%	55%	44%		54%	53%	49%
57.4%	61%	62%		50%	55%	59%
47.6%	41%	54%		49%	52%	42%
71.8%	75%	73%		76%	65%	70%
58.6%	66%	80%		59%	44%	44%
78.8%	78%	84%		82%	76%	74%
70.8%	71%	74%		73%	70%	66%
58.4%	49%	60%		59%	79%	45%
68.6%	64%	68%		72%	73%	66%
68.0%	73%	81%		70%	58%	58%
44.4%	50%	33%		44%	51%	44%
64.4%	65%	65%		65%	71%	56%
76.4%	77%	78%		77%	77%	73%
47.2%	53%	47%		53%	41%	42%
54.0%	64%	56%		41%	68%	41%
53.6%	63%	67%		58%	43%	37%
77.0%	77%	71%		72%	82%	83%
65.8%	63%	65%		64%	73%	64%
88.6%	89%	86%		90%	88%	90%
72.2%	79%	68%		75%	74%	65%
61.4%	70%	72%		56%	64%	45%
45.0%	59%	31%		45%	45%	45%
64.4%	70%	58%		65%	62%	67%
43.4%	41%	39%		42%	44%	51%
57.8%	60%	65%		50%	54%	60%
50.2%	52%	54%		51%	51%	43%
27.8%	26%	28%		29%	29%	27%
55.8%	44%	62%		51%	72%	50%
63.6%	67%	66%		63%	71%	51%
45.6%	48%	41%		47%	45%	47%
59.6%	65%	64%		57%	56%	56%
66.8%	69%	70%		66%	73%	56%
55.6%	54%	68%		50%	68%	38%
62.4%	63%	66%		61%	75%	47%
48.6%	52%	62%		37%	57%	35%
75.2%	81%	73%		86%	50%	86%
39.6%	41%	42%		42%	36%	37%
40.4%	47%	36%		37%	41%	41%
26.6%	39%	22%		24%	24%	24%
63.0%	64%	68%		62%	71%	50%
89.6%	98%	92%		80%	88%	90%
53.0%	59%	77%		43%	43%	43%
77.2%	75%	73%		78%	83%	77%
67.0%	64%	64%		72%	69%	66%
82.6%	74%	82%		86%	76%	95%
57.4%	58%	42%		63%	61%	63%