	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 62.9%	2nd 62.9%	1st 76.0%	4th 61.8%	6th 53.4%	5th 59.5%
48.2%	43%	51%		48%	37%	62%
46.0%	47%	49%		40%	51%	43%
47.8%	58%	49%		40%	43%	49%
52.4%	51%	49%		58%	55%	49%
53.2%	56%	58%		47%	55%	50%
62.2%	51%	70%		58%	66%	66%
75.4%	79%	65%		80%	80%	73%
63.4%	70%	51%		67%	67%	62%
68.4%	74%	67%		78%	63%	60%
65.4%	82%	76%		62%	47%	60%
63.8%	69%	83%		59%	47%	61%
39.4%	34%	47%		45%	31%	40%
61.4%	78%	84%		68%	21%	56%
51.4%	50%	49%		58%	42%	58%
66.2%	56%	63%		69%	75%	68%
42.2%	45%	47%		43%	34%	42%
75.2%	84%	74%		72%	71%	75%
70.4%	71%	71%		73%	73%	64%
66.4%	71%	76%		64%	57%	64%
47.4%	55%	61%		55%	24%	42%
59.0%	62%	62%		62%	58%	51%
61.6%	68%	62%		65%	54%	59%
82.8%	80%	87%		73%	91%	83%
53.2%	61%	39%		56%	55%	55%
61.4%	78%	84%		68%	21%	56%
61.4%	60%	70%		69%	42%	66%
56.8%	53%	47%		59%	57%	68%
58.4%	64%	51%		62%	50%	65%
86.2%	93%	81%		90%	86%	81%
52.0%	46%	62%		51%	50%	51%
41.6%	43%	33%		45%	27%	60%
81.4%	87%	87%		80%	78%	75%
68.7%	77%	70%	76%	68%	60%	61%
63.2%	63%	66%		63%	59%	65%
47.0%	43%	54%		48%	41%	49%
60.4%	67%	54%		54%	65%	62%
65.2%	61%	70%		64%	64%	67%
50.4%	52%	44%		49%	52%	55%
42.2%	35%	55%		55%	24%	42%
67.8%	76%	74%		64%	57%	68%
77.2%	87%	80%		80%	54%	85%
46.2%	54%	47%		45%	63%	22%
58.2%	61%	64%		60%	57%	49%
66.0%	63%	65%		74%	54%	74%
52.2%	48%	60%		66%	32%	55%
80.0%	87%	87%		90%	65%	71%