	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 66.7%	3rd 64.6%	- -	1st 67.2%	5th 61.6%	4th 64.5%
59.2%	62%	53%		63%	63%	55%
61.6%	64%	71%		54%	67%	52%
44.4%	54%	42%		51%	37%	38%
91.0%	91%	91%		91%	91%	91%
46.2%	37%	46%		43%	55%	50%
79.6%	67%	88%		75%	84%	84%
63.8%	58%	68%		61%	66%	66%
62.8%	70%	51%		60%	68%	65%
60.8%	53%	87%		75%	41%	48%
73.0%	61%	73%		79%	74%	78%
60.4%	69%	74%		61%	49%	49%
51.4%	61%	39%		61%	40%	56%
71.0%	79%	69%		84%	54%	69%
91.0%	91%	91%		91%	91%	91%
54.0%	62%	40%		55%	60%	53%
48.8%	50%	48%		48%	48%	50%
69.4%	70%	71%		76%	58%	72%
67.4%	69%	70%		66%	66%	66%
61.8%	66%	69%		58%	58%	58%
51.4%	61%	49%		61%	43%	43%
65.4%	69%	69%		64%	58%	67%
67.0%	83%	30%		75%	63%	84%
85.4%	87%	83%		83%	91%	83%
43.0%	32%	58%		39%	43%	43%
71.0%	79%	69%		84%	54%	69%
60.6%	65%	62%		75%	39%	62%
64.2%	73%	22%		73%	80%	73%
72.4%	80%	62%		82%	65%	73%
89.6%	87%	91%		83%	96%	91%
47.6%	57%	38%		50%	51%	42%
77.6%	76%	86%		86%	63%	77%
58.4%	63%	57%		63%	54%	55%
66.8%	65%	66%		77%	64%	62%
63.4%	57%	73%		60%	60%	67%
80.2%	77%	86%		76%	77%	85%
86.4%	90%	79%		78%	90%	95%
73.4%	76%	60%		77%	77%	77%
48.6%	51%	63%		47%	41%	41%
48.6%	57%	43%		57%	38%	48%
80.8%	77%	90%		71%	76%	90%
62.0%	65%	67%		59%	58%	61%
52.2%	46%	58%		60%	60%	37%
56.8%	55%	68%		54%	55%	52%
67.4%	70%	65%		81%	56%	65%
69.4%	70%	73%		63%	67%	74%
58.4%	67%	63%		59%	44%	59%