	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 80.3%	3rd 78.7%	1st 88.0%	4th 77.9%	6th 73.2%	5th 75.7%
64.4%	78%	58%		63%	63%	60%
86.8%	91%	85%		87%	78%	93%
82.6%	91%	95%		78%	75%	74%
74.4%	78%	80%		74%	69%	71%
71.0%	78%	57%		69%	62%	89%
74.6%	75%	77%		76%	77%	68%
88.4%	92%	90%		90%	89%	81%
46.8%	76%	8%		45%	60%	45%
72.2%	65%	76%		77%	70%	73%
79.6%	74%	83%		82%	76%	83%
88.2%	85%	96%		84%	88%	88%
85.4%	84%	87%		86%	81%	89%
56.6%	64%	76%		56%	44%	43%
87.0%	95%	84%		88%	78%	90%
84.4%	89%	87%		86%	77%	83%
88.8%	90%	96%		88%	79%	91%
76.2%	78%	83%		77%	72%	71%
83.8%	83%	94%		86%	75%	81%
60.2%	65%	72%		65%	46%	53%
76.0%	78%	78%		77%	80%	67%
88.4%	86%	86%		93%	87%	90%
84.2%	86%	86%		88%	82%	79%
50.8%	55%	53%		41%	63%	42%
80.8%	87%	74%		81%	78%	84%
83.4%	87%	89%		83%	72%	86%
85.2%	93%	91%		85%	65%	92%
92.4%	90%	91%		96%	91%	94%
74.4%	85%	80%		72%	75%	60%
80.4%	88%	80%		82%	80%	72%
64.4%	70%	75%		62%	51%	64%
71.8%	74%	67%		75%	70%	73%
72.4%	77%	66%		74%	61%	84%
79.4%	73%	83%		83%	82%	76%
83.6%	85%	88%		86%	73%	86%
52.6%	60%	53%		41%	56%	53%
86.2%	82%	95%		87%	85%	82%
81.6%	86%	82%		87%	78%	75%
60.2%	61%	55%		69%	58%	58%
88.0%	86%	88%		93%	85%	88%
84.8%	77%	91%	88%	89%	88%	76%
83.0%	82%	83%		82%	88%	80%
73.0%	76%	78%		72%	76%	63%
73.8%	77%	79%		75%	72%	66%
88.2%	96%	87%		94%	83%	81%
80.8%	82%	77%		78%	82%	85%
69.8%	75%	70%		68%	62%	74%
51.0%	59%	56%		60%	29%	51%
68.8%	71%	66%		73%	72%	62%
86.2%	89%	91%		76%	90%	85%
78.4%	80%	93%		82%	62%	75%
82.0%	87%	89%		88%	60%	86%
91.0%	89%	89%		91%	93%	93%
90.0%	83%	91%		91%	91%	94%
79.2%	93%	68%		78%	72%	85%