	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 65.6%	5th 61.6%	1st 79.0%	3rd 65.2%	6th 56.4%	4th 63.4%
59.7%	73%	24%	58%	73%	65%	65%
51.6%	59%	54%		46%	51%	48%
77.2%	73%	80%		83%	67%	83%
100.0%	100%	100%	100%	100%	100%	100%
86.2%	85%	92%		96%	79%	79%
72.6%	76%	82%		69%	68%	68%
69.2%	65%	63%		69%	72%	77%
47.2%	50%	48%		33%	48%	57%
47.6%	64%	56%		64%	28%	26%
76.4%	83%	95%		72%	65%	67%
62.4%	72%	64%		56%	66%	54%
62.8%	63%	53%		76%	54%	68%
69.2%	71%	95%		77%	45%	58%
100.0%	100%	100%		100%	100%	100%
52.8%	52%	40%		62%	53%	57%
45.4%	55%	32%		55%	41%	44%
75.6%	76%	81%		81%	70%	70%
46.4%	48%	35%		47%	35%	67%
64.2%	59%	68%		69%	70%	55%
65.6%	69%	70%		75%	54%	60%
59.2%	79%	43%		70%	21%	83%
50.6%	60%	48%		53%	48%	44%
83.8%	71%	84%		92%	80%	92%
42.4%	44%	43%		38%	42%	45%
70.4%	77%	87%		75%	49%	64%
65.4%	64%	61%		74%	54%	74%
46.2%	57%	28%		46%	30%	70%
52.6%	54%	47%		50%	56%	56%
92.0%	85%	96%		87%	96%	96%
62.2%	78%	80%		64%	28%	61%
43.8%	53%	0%		64%	51%	51%
66.6%	70%	59%		69%	71%	64%
65.6%	66%	53%		67%	67%	75%
74.6%	83%	55%		64%	81%	90%
67.4%	71%	66%		74%	63%	63%
38.0%	28%	59%		29%	37%	37%
57.4%	70%	38%		64%	76%	39%
41.2%	45%	53%		36%	32%	40%
52.0%	51%	49%		59%	43%	58%
82.8%	78%	78%		80%	82%	96%
64.4%	83%	69%		72%	26%	72%
34.8%	29%	51%		39%	36%	19%
61.4%	54%	95%		51%	56%	51%
52.4%	51%	50%		60%	41%	60%
62.2%	65%	61%		66%	62%	57%
50.4%	60%	50%		51%	36%	55%