	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 65.5%	3rd 63.1%	5th 62.6%	1st 67.0%	6th 59.6%	4th 62.6%
52.4%	46%	60%		62%	49%	45%
58.8%	64%	58%		58%	65%	49%
43.4%	54%	51%		42%	37%	33%
91.0%	91%	91%		91%	91%	91%
41.8%	33%	45%	36%	37%	45%	55%
83.3%	80%	88%	82%	83%	84%	83%
65.4%	58%	64%		61%	70%	74%
54.6%	59%	28%		65%	63%	58%
62.6%	62%	58%		80%	51%	62%
72.4%	66%	67%		79%	72%	78%
59.8%	73%	61%		61%	61%	43%
51.0%	47%	47%		65%	40%	56%
73.2%	75%	91%		84%	54%	62%
91.0%	91%	91%		91%	91%	91%
54.0%	62%	40%		53%	62%	53%
36.4%	35%	20%		57%	42%	28%
66.6%	72%	72%		73%	58%	58%
65.6%	65%	66%		66%	66%	65%
62.0%	62%	74%		58%	58%	58%
50.8%	61%	46%		61%	43%	43%
64.0%	65%	66%	61%	67%	58%	67%
65.8%	71%	30%	61%	71%	79%	83%
82.0%	80%	91%		73%	83%	83%
53.0%	54%	77%		46%	39%	49%
57.0%	75%	10%		84%	54%	62%
64.8%	67%	75%		69%	55%	58%
67.2%	82%	42%		73%	66%	73%
73.8%	76%	73%		82%	65%	73%
86.6%	80%	83%		83%	96%	91%
50.2%	55%	57%		42%	57%	40%
69.6%	68%	68%		78%	69%	65%
58.0%	67%	57%		63%	59%	44%
64.2%	67%	66%		75%	51%	62%
62.2%	67%	57%		60%	60%	67%
80.8%	78%	82%		82%	77%	85%
85.0%	80%	90%		83%	82%	90%
66.4%	68%	62%		75%	65%	62%
47.0%	51%	63%		47%	33%	41%
45.5%	48%	48%	39%	57%	33%	48%
80.2%	76%	91%	83%	65%	76%	90%
55.4%	66%	77%		67%	9%	58%
55.6%	53%	63%		56%	56%	50%
55.0%	58%	55%		55%	55%	52%
66.8%	70%	65%		78%	56%	65%
70.2%	70%	73%	76%	65%	68%	69%
58.4%	66%	63%		59%	37%	67%