	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 71.3%	4th 66.7%	- -	1st 72.5%	5th 65.7%	3rd 70.5%
64.6%	65%	73%		67%	46%	72%
64.6%	65%	35%		76%	74%	73%
73.4%	72%	57%		77%	84%	77%
71.4%	82%	73%		76%	64%	62%
85.0%	83%	89%		82%	78%	93%
86.4%	89%	75%		83%	92%	93%
81.6%	87%	77%		76%	84%	84%
81.8%	85%	69%		84%	86%	85%
80.2%	83%	87%		76%	76%	79%
66.4%	73%	64%		64%	67%	64%
70.8%	75%	75%		67%	70%	67%
71.6%	77%	62%		66%	79%	74%
80.4%	85%	85%		90%	59%	83%
59.4%	63%	78%		78%	39%	39%
66.8%	67%	59%		82%	53%	73%
69.8%	74%	66%		79%	56%	74%
76.2%	83%	94%		83%	54%	67%
54.2%	50%	58%		52%	61%	50%
46.8%	34%	63%		41%	34%	62%
78.6%	73%	77%		77%	80%	86%
67.0%	70%	51%		70%	67%	77%
59.6%	57%	35%		74%	66%	66%
52.6%	68%	52%		53%	36%	54%
72.2%	64%	93%		64%	67%	73%
48.2%	52%	37%		78%	37%	37%
73.4%	64%	76%		82%	69%	76%
56.2%	63%	61%		57%	38%	62%
74.8%	79%	62%		82%	79%	72%
73.0%	87%	83%		56%	68%	71%
67.2%	69%	72%		64%	71%	60%
54.0%	50%	50%		69%	39%	62%
56.0%	61%	72%		51%	45%	51%
72.4%	67%	57%		77%	84%	77%
78.4%	83%	62%		87%	80%	80%
53.6%	67%	36%		52%	51%	62%
61.4%	67%	35%		63%	74%	68%
69.0%	60%	76%		83%	54%	72%
89.0%	94%	93%		94%	84%	80%
59.0%	48%	48%		65%	69%	65%
89.8%	100%	89%		89%	82%	89%
75.2%	76%	68%		76%	78%	78%
63.4%	66%	56%		67%	66%	62%
85.2%	88%	88%		88%	83%	79%