	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 74.6%	1st 76.3%	- -	3rd 72.1%	5th 68.6%	4th 70.3%
47.8%	53%	52%		52%	38%	44%
83.6%	83%	80%		84%	79%	92%
82.0%	89%	82%		84%	79%	76%
70.2%	72%	70%		72%	65%	72%
63.0%	71%	50%		66%	51%	77%
75.0%	75%	78%		74%	80%	68%
81.4%	86%	81%		80%	81%	79%
59.8%	67%	95%		38%	57%	42%
70.8%	75%	78%		72%	66%	63%
70.0%	73%	84%		59%	69%	65%
93.4%	89%	97%		89%	95%	97%
78.6%	75%	63%		86%	84%	85%
56.6%	65%	70%		58%	45%	45%
85.2%	90%	90%		82%	82%	82%
78.4%	84%	86%		73%	78%	71%
83.8%	87%	79%		86%	79%	88%
71.2%	73%	80%		77%	67%	59%
70.8%	70%	89%		66%	58%	71%
53.6%	53%	76%		56%	32%	51%
67.2%	76%	77%		60%	67%	56%
82.6%	84%	88%		77%	88%	76%
78.4%	88%	79%		80%	77%	68%
53.8%	58%	57%		42%	63%	49%
76.4%	82%	77%		80%	72%	71%
84.6%	85%	87%		85%	85%	81%
84.6%	88%	85%		84%	81%	85%
95.2%	98%	86%		98%	97%	97%
72.6%	78%	91%		67%	72%	55%
77.4%	84%	79%		82%	72%	70%
46.0%	41%	66%		47%	29%	47%
70.6%	71%	66%		73%	67%	76%
63.0%	61%	64%		66%	49%	75%
67.0%	69%	73%		61%	67%	65%
76.2%	76%	68%		83%	74%	80%
35.8%	25%	49%		33%	30%	42%
81.6%	80%	83%		84%	80%	81%
76.4%	82%	76%		75%	74%	75%
45.6%	42%	57%		43%	43%	43%
87.0%	90%	84%		84%	88%	89%
86.2%	84%	93%		87%	89%	78%
83.2%	82%	80%		84%	86%	84%
64.6%	73%	70%		59%	65%	56%
68.4%	67%	85%		66%	58%	66%
87.4%	89%	84%		88%	92%	84%
75.8%	77%	73%		74%	77%	78%
56.4%	49%	59%		56%	49%	69%
52.6%	61%	64%		59%	30%	49%
69.2%	72%	79%		70%	67%	58%
71.2%	78%	85%		68%	62%	63%
74.2%	82%	75%		82%	57%	75%
80.0%	84%	83%		81%	71%	81%
84.6%	84%	77%		83%	91%	88%
83.8%	90%	81%		88%	79%	81%
73.2%	69%	58%		88%	71%	80%