	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 70.5%	4th 64.7%	- -	1st 71.2%	5th 63.2%	3rd 69.5%
64.2%	65%	67%		67%	55%	67%
61.0%	62%	34%		64%	74%	71%
74.0%	75%	57%		77%	84%	77%
70.2%	83%	78%		64%	64%	62%
84.6%	83%	89%		75%	87%	89%
87.8%	86%	83%		83%	88%	99%
72.4%	77%	54%		75%	76%	80%
80.2%	85%	70%		85%	77%	84%
78.4%	74%	84%		76%	76%	82%
65.4%	66%	64%		63%	63%	71%
69.2%	75%	72%		71%	70%	58%
74.2%	77%	66%		77%	79%	72%
77.0%	83%	75%		88%	56%	83%
47.8%	59%	50%		43%	43%	44%
71.2%	75%	75%		82%	55%	69%
71.4%	75%	60%		79%	61%	82%
72.8%	83%	78%		83%	53%	67%
58.2%	50%	77%		51%	71%	42%
36.6%	30%	63%		33%	23%	34%
71.0%	56%	76%		72%	76%	75%
62.8%	70%	63%		70%	37%	74%
59.6%	67%	49%		74%	43%	65%
53.2%	50%	54%		53%	56%	53%
68.6%	73%	82%		64%	44%	80%
46.2%	57%	28%		57%	45%	44%
53.2%	67%	41%		58%	27%	73%
57.6%	63%	54%		57%	58%	56%
73.0%	77%	60%		82%	72%	74%
73.8%	80%	83%		72%	63%	71%
68.2%	69%	77%		75%	61%	59%
53.4%	55%	49%		69%	39%	55%
57.6%	53%	72%		51%	61%	51%
72.0%	75%	57%		67%	84%	77%
75.8%	79%	65%		79%	82%	74%
57.2%	64%	31%		67%	54%	70%
58.2%	65%	35%		63%	60%	68%
66.4%	66%	83%		83%	36%	64%
89.4%	96%	93%		94%	84%	80%
60.4%	64%	55%		65%	52%	66%
93.8%	91%	89%		100%	100%	89%
73.8%	77%	58%		78%	73%	83%
64.8%	67%	56%		74%	56%	71%
89.6%	88%	77%		100%	100%	83%