	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 66.6%	6th 56.3%	5th 57.9%	2nd 64.1%	4th 61.8%	3rd 63.6%
37.2%		56%	16%	36%	41%	37%
45.4%		82%	18%	47%	40%	40%
66.6%		41%	70%	77%	73%	72%
55.8%		47%	56%	57%	55%	64%
61.4%		63%	61%	62%	60%	61%
63.4%		68%	54%	64%	53%	78%
62.3%	78%	67%	47%	45%	79%	58%
57.4%		47%	52%	70%	59%	59%
68.4%		56%	74%	83%	67%	62%
65.8%		20%	78%	58%	88%	85%
56.2%		77%	41%	58%	49%	56%
67.0%		50%	70%	67%	72%	76%
60.6%		74%	58%	58%	58%	55%
53.6%		54%	48%	66%	39%	61%
64.4%		42%	66%	72%	76%	66%
66.0%		77%	60%	64%	54%	75%
65.8%		78%	67%	62%	52%	70%
71.8%		75%	69%	76%	65%	74%
73.0%		64%	57%	76%	92%	76%
79.2%	92%	77%	51%	88%	82%	85%
62.2%		48%	68%	65%	62%	68%
60.8%		24%	74%	70%	56%	80%
52.8%		55%	48%	58%	36%	67%
64.0%		68%	64%	64%	66%	58%
63.2%		47%	58%	75%	64%	72%
85.0%		85%	85%	85%	85%	85%
69.4%		64%	71%	71%	70%	71%
58.0%		68%	38%	68%	70%	46%
42.0%	49%	45%	37%	38%	48%	35%
60.6%		55%	51%	64%	64%	69%
75.2%		47%	71%	84%	84%	90%
62.6%		41%	69%	71%	64%	68%
62.2%		72%	60%	68%	46%	65%
51.2%		65%	50%	54%	36%	51%
57.6%		69%	45%	67%	51%	56%
64.8%		46%	68%	67%	69%	74%
44.2%		34%	48%	47%	36%	56%
37.0%		36%	39%	37%	37%	36%
56.2%		44%	53%	66%	54%	64%
72.6%		79%	71%	72%	74%	67%
65.0%		54%	60%	83%	58%	70%
53.6%		29%	73%	52%	62%	52%
53.8%		71%	45%	50%	42%	61%
69.4%		64%	76%	63%	70%	74%
71.6%		93%	56%	70%	67%	72%
78.2%		71%	76%	92%	78%	74%
52.6%		60%	60%	48%	46%	49%
74.8%		67%	57%	79%	72%	99%
48.6%		24%	56%	55%	53%	55%
71.0%		69%	69%	70%	76%	71%
60.8%		61%	58%	51%	76%	58%
48.2%		0%	58%	65%	62%	56%
60.6%		73%	44%	70%	52%	64%
62.0%		53%	61%	58%	69%	69%
41.0%		33%	33%	41%	47%	51%
68.2%		60%	69%	70%	70%	72%
60.8%		19%	65%	64%	81%	75%
52.6%		80%	40%	47%	53%	43%
49.2%		75%	42%	50%	32%	47%
70.8%		51%	84%	79%	71%	69%
69.2%		54%	79%	72%	71%	70%
53.6%		81%	43%	39%	66%	39%
66.4%		70%	80%	68%	59%	55%
64.0%		54%	60%	71%	64%	71%
51.6%		60%	50%	45%	34%	69%
55.2%		89%	53%	43%	38%	53%
49.4%		68%	45%	43%	48%	43%
61.4%		46%	64%	62%	68%	67%
56.6%		50%	59%	62%	55%	57%
63.0%		48%	62%	71%	68%	66%
63.0%		65%	67%	64%	59%	60%
63.4%		46%	73%	70%	64%	64%
71.6%		78%	67%	77%	65%	71%
61.6%		42%	77%	65%	59%	65%
52.8%		56%	48%	55%	51%	54%
61.2%		41%	71%	61%	60%	73%
75.0%		59%	75%	81%	82%	78%
68.0%		55%	63%	75%	75%	72%
59.6%		78%	40%	57%	54%	69%
59.0%		50%	53%	70%	62%	60%
71.2%		64%	65%	76%	76%	75%
55.8%		58%	42%	63%	74%	42%
53.6%		66%	51%	55%	45%	51%
58.8%		20%	64%	76%	58%	76%
74.4%		73%	67%	80%	80%	72%
54.4%		61%	48%	58%	51%	54%
56.8%		55%	52%	51%	63%	63%
74.8%		68%	75%	83%	78%	70%
65.2%		48%	54%	75%	71%	78%
64.4%		61%	55%	71%	78%	57%
59.2%		61%	54%	51%	64%	66%
69.6%		69%	63%	70%	74%	72%
42.8%		16%	48%	40%	61%	49%
51.8%	57%	60%	30%	63%	57%	44%
72.8%		61%	69%	78%	78%	78%
52.4%		40%	51%	56%	49%	66%
68.0%		42%	78%	67%	77%	76%
43.0%		12%	55%	48%	48%	52%
61.4%		59%	42%	79%	60%	67%
49.2%		20%	58%	51%	58%	59%
37.0%		0%	46%	56%	45%	38%
63.8%		83%	62%	57%	61%	56%
76.6%		85%	78%	66%	85%	69%
52.2%		56%	26%	58%	63%	58%
38.4%		52%	26%	35%	52%	27%
50.2%		15%	49%	71%	59%	57%
68.4%		47%	65%	97%	66%	67%
42.0%		71%	21%	43%	36%	39%
65.5%	57%	58%	70%	63%	59%	86%
65.0%		78%	73%	57%	50%	67%
56.4%		53%	50%	58%	54%	67%
55.6%		65%	44%	66%	52%	51%
80.6%		85%	74%	78%	85%	81%
75.6%		51%	82%	86%	76%	83%
71.8%		64%	62%	76%	90%	67%
72.6%		51%	70%	89%	75%	78%