	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 66.0%	4th 64.5%	1st 89.0%	3rd 65.0%	6th 61.3%	5th 62.6%
63.0%	71%	65%		61%	65%	53%
71.4%	73%	73%		73%	65%	73%
74.6%	74%	81%		81%	65%	72%
59.6%	63%	61%		53%	56%	65%
61.0%	74%	22%		61%	79%	69%
59.4%	64%	65%		66%	65%	37%
70.0%	70%	76%		68%	68%	68%
60.8%	72%	100%		44%	51%	37%
49.6%	49%	54%		48%	49%	48%
70.6%	71%	71%		73%	67%	71%
70.8%	72%	69%		71%	71%	71%
46.0%	43%	40%		49%	49%	49%
66.2%	79%	84%		73%	35%	60%
51.6%	48%	60%		56%	38%	56%
53.2%	55%	54%		54%	49%	54%
77.0%	77%	82%		81%	74%	71%
62.0%	61%	59%		65%	65%	60%
70.8%	69%	74%		73%	70%	68%
67.6%	70%	64%		67%	73%	64%
73.0%	74%	72%		77%	70%	72%
39.4%	43%	36%		43%	32%	43%
50.2%	50%	49%		49%	40%	63%
56.8%	66%	60%		42%	74%	42%
63.4%	61%	47%		73%	67%	69%
43.4%	45%	43%		43%	35%	51%
47.8%	51%	51%		53%	35%	49%
89.0%	90%	100%		86%	82%	87%
57.0%	63%	57%		58%	53%	54%
50.8%	55%	48%		71%	36%	44%
72.8%	70%	75%		78%	63%	78%
47.6%	36%	51%		48%	44%	59%
54.4%	50%	59%		57%	49%	57%
83.6%	77%	81%		89%	90%	81%
75.0%	77%	77%		76%	72%	73%
42.6%	51%	44%		44%	44%	30%
72.8%	75%	74%			68%	74%
61.2%	59%	66%		58%	61%	62%
69.0%	73%	65%		73%	72%	62%
66.8%	66%	62%		67%	69%	70%
79.6%	77%	78%		78%	87%	78%
84.3%	87%	86%	89%	90%	81%	73%
63.0%	67%	64%		60%	62%	62%
81.4%	83%	87%		79%	77%	81%
50.6%	64%	44%		57%	51%	37%
94.0%	98%	86%		100%	86%	100%
69.6%	63%	65%		65%	75%	80%
64.0%	67%	67%		77%	53%	56%
55.4%	62%	49%		54%	58%	54%
82.8%	79%	87%		78%	82%	88%
44.6%	44%	48%		48%	37%	46%
57.4%	67%	61%		61%	45%	53%
72.8%	79%	64%		70%	79%	72%
66.8%	66%	82%		60%	66%	60%
64.0%	74%	44%		67%	62%	73%