	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 83.1%	2nd 81.6%	- -	3rd 81.3%	4th 77.5%	5th 77.3%
54.8%	62%	43%		59%	64%	46%
83.6%	93%	93%		91%	73%	68%
83.4%	87%	92%		86%	72%	80%
76.0%	79%	79%		68%	73%	81%
67.2%	88%	49%		61%	71%	67%
82.8%	88%	93%		83%	86%	64%
87.8%	90%	90%		89%	83%	87%
60.6%	67%	97%		38%	49%	52%
73.0%	73%	69%		73%	78%	72%
83.8%	80%	87%		86%	84%	82%
83.2%	81%	83%		88%	84%	80%
85.8%	83%	78%		91%	88%	89%
60.0%	69%	80%		64%	43%	44%
89.8%	94%	91%		93%	83%	88%
89.6%	93%	94%		90%	89%	82%
84.6%	91%	94%		94%	75%	69%
73.8%	75%	86%		75%	69%	64%
82.4%	89%	62%		95%	82%	84%
84.2%	86%	89%		80%	87%	79%
83.6%	89%	87%		85%	80%	77%
89.0%	87%	82%		92%	91%	93%
93.8%	94%	94%		94%	97%	90%
62.0%	67%	68%		46%	79%	50%
82.4%	88%	75%		88%	81%	80%
88.2%	83%	88%		90%	90%	90%
88.8%	96%	93%		93%	69%	93%
91.0%	92%	84%		95%	92%	92%
82.2%	92%	97%		80%	71%	71%
81.0%	86%	82%		88%	71%	78%
87.6%	88%	91%		77%	91%	91%
57.8%	55%	76%		65%	39%	54%
83.6%	90%	61%		94%	87%	86%
85.6%	78%	91%		86%	86%	87%
81.0%	82%	79%		85%	77%	82%
55.0%	69%	53%		57%	50%	46%
84.4%	90%	95%		80%	80%	77%
81.6%	83%	86%		82%	77%	80%
80.0%	73%	70%		89%	89%	79%
83.0%	71%	81%		94%	83%	86%
84.8%	77%	84%		89%	87%	87%
78.0%	81%	72%		80%	78%	79%
76.2%	79%	80%		69%	79%	74%
79.2%	87%	81%		80%	70%	78%
87.4%	96%	86%		93%	81%	81%
83.2%	85%	79%		80%	85%	87%
87.6%	82%	96%		89%	91%	80%
64.2%	82%	65%		60%	54%	60%
72.2%	76%	83%		61%	77%	64%
86.0%	87%	92%		83%	78%	90%
76.2%	69%	88%		75%	75%	74%
86.2%	96%	86%		90%	72%	87%
86.8%	87%	81%		95%	86%	85%
92.4%	93%	89%		95%	90%	95%
79.4%	89%	61%		88%	68%	91%