	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 74.8%	1st 76.3%	- -	3rd 72.5%	4th 72.4%	5th 71.2%
82.6%	83%	90%		81%	81%	78%
62.2%	62%	59%		62%	63%	65%
79.8%	74%	76%		78%	93%	78%
71.0%	74%	74%		65%	74%	68%
81.4%	83%	80%		79%	80%	85%
84.6%	95%	96%		79%	79%	74%
64.2%	58%	74%		60%	74%	55%
73.8%	65%	78%		60%	88%	78%
77.2%	74%	76%		73%	86%	77%
60.6%	69%	61%		60%	52%	61%
73.6%	84%	71%		84%	62%	67%
50.6%	60%	50%		41%	50%	52%
84.0%	87%	89%		87%	68%	89%
85.2%	84%	93%		90%	77%	82%
84.2%	82%	87%		90%	74%	88%
68.4%	70%	71%		68%	70%	63%
78.8%	82%	89%		74%	77%	72%
52.8%	56%	50%		52%	61%	45%
56.6%	56%	53%		62%	54%	58%
61.8%	49%	69%		59%	75%	57%
77.2%	73%	78%		77%	86%	72%
81.2%	82%	89%		82%	74%	79%
65.0%	71%	76%		63%	52%	63%
78.6%	81%	78%		83%	68%	83%
79.2%	86%	83%		86%	69%	72%
69.2%	70%	70%		69%	66%	71%
61.2%	64%	70%		54%	69%	49%
84.4%	90%	89%		86%	80%	77%
55.4%	72%	64%		55%	35%	51%
68.6%	63%	72%		64%	88%	56%
81.2%	89%	82%		82%	73%	80%
74.4%	77%	80%		77%	62%	76%
89.0%	87%	81%		92%	98%	87%
62.6%	49%	81%		53%	74%	56%
69.2%	78%	65%		62%	64%	77%
65.4%	69%	56%		64%	73%	65%
84.2%	87%	89%		83%	79%	83%
88.0%	88%	89%		93%	77%	93%
82.0%	84%	88%		83%	82%	73%
65.2%	64%	61%		64%	72%	65%
78.8%	80%	81%		81%	76%	76%
78.8%	84%	81%		77%	78%	74%
85.4%	80%	90%		85%	82%	90%