	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 68.4%	4th 64.0%	- -	1st 68.6%	5th 60.2%	3rd 66.6%
47.6%	53%	0%		56%	56%	73%
47.0%	50%	52%		39%	53%	41%
57.8%	63%	56%		57%	57%	56%
57.4%	58%	57%		58%	57%	57%
68.0%	68%	71%		62%	69%	70%
65.8%	59%	68%		68%	67%	67%
78.8%	84%	85%		79%	76%	70%
56.2%	61%	49%		52%	61%	58%
71.8%	69%	80%		78%	65%	67%
72.0%	78%	82%		69%	65%	66%
63.8%	71%	72%		67%	50%	59%
63.0%	67%	63%		60%	58%	67%
67.2%	77%	81%		79%	36%	63%
59.4%	61%	55%		61%	60%	60%
57.4%	59%	48%		59%	64%	57%
77.2%	78%	76%		82%	66%	84%
68.6%	75%	73%		65%	66%	64%
76.6%	78%	79%		73%	82%	71%
55.2%	59%	65%		50%	48%	54%
51.8%	66%	0%		73%	54%	66%
57.4%	59%	61%		56%	59%	52%
70.4%	84%	50%		76%	56%	86%
84.8%	92%	65%		100%	86%	81%
65.0%	62%	75%		66%	56%	66%
60.2%	73%	74%		69%	30%	55%
58.8%	59%	64%		66%	40%	65%
69.6%	68%	60%		76%	71%	73%
61.2%	64%	56%		66%	56%	64%
87.6%	83%	85%		82%	94%	94%
69.2%	75%	70%		68%	65%	68%
57.2%	49%	60%		61%	50%	66%
72.2%	71%	72%		73%	75%	70%
72.0%	69%	71%		71%	72%	77%
65.6%	59%	75%		65%	61%	68%
75.4%	77%	80%		82%	59%	79%
72.8%	73%	73%		78%	69%	71%
55.4%	75%	0%		68%	65%	69%
65.2%	72%	77%		70%	50%	57%
53.0%	53%	59%		66%	34%	53%
68.2%	72%	73%		72%	53%	71%
72.6%	78%	70%		81%	59%	75%
74.0%	73%	69%		79%	68%	81%
55.8%	57%	75%		53%	51%	43%
63.6%	59%	69%		69%	51%	70%
82.8%	87%	83%		90%	65%	89%
62.4%	71%	65%		65%	62%	49%