	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 74.0%	1st 75.3%	- -	2nd 74.2%	5th 66.7%	4th 73.0%
73.2%	69%	75%		77%	68%	77%
65.8%	69%	67%		62%	70%	61%
64.4%	69%	72%		68%	54%	59%
76.4%	77%	72%		77%	78%	78%
83.6%	85%	87%		86%	69%	91%
74.0%	68%	80%		74%	74%	74%
76.4%	76%	84%		74%	74%	74%
69.8%	71%	75%		62%	75%	66%
77.6%	78%	79%		80%	74%	77%
82.4%	78%	90%		87%	81%	76%
59.8%	65%	78%		59%	42%	55%
66.0%	60%	66%		72%	55%	77%
83.8%	95%	93%		91%	62%	78%
76.4%	77%	72%		77%	78%	78%
58.8%	56%	51%		59%	61%	67%
52.8%	56%	55%		56%	40%	57%
66.0%	74%	75%		65%	49%	67%
84.8%	88%	85%		86%	86%	79%
72.8%	74%	76%		72%	70%	72%
45.8%	51%	54%		53%	22%	49%
69.6%	68%	68%		71%	68%	73%
78.4%	88%	56%		78%	80%	90%
94.2%	96%	94%		91%	94%	96%
63.8%	63%	69%		63%	63%	61%
82.2%	89%	90%		98%	59%	75%
68.2%	69%	78%		66%	48%	80%
75.2%	74%	63%		79%	81%	79%
86.0%	89%	89%		89%	79%	84%
88.2%	83%	83%		87%	94%	94%
83.4%	84%	86%		81%	85%	81%
52.2%	45%	56%		60%	40%	60%
86.2%	87%	91%		85%	83%	85%
63.8%	61%	70%		63%	67%	58%
73.6%	68%	84%		70%	70%	76%
81.4%	87%	74%		81%	86%	79%
85.4%	82%	86%		87%	86%	86%
64.6%	69%	63%		63%	61%	67%
49.4%	53%	54%		56%	39%	45%
46.2%	47%	49%		57%	29%	49%
87.2%	94%	89%		92%	78%	83%
68.4%	73%	82%		69%	49%	69%
73.2%	75%	73%		73%	69%	76%
63.4%	64%	69%		64%	64%	56%
84.6%	81%	89%		91%	71%	91%
80.2%	81%	87%		85%	63%	85%
82.4%	97%	86%		79%	80%	70%