	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 76.1%	2nd 75.7%	- -	3rd 74.5%	5th 70.1%	4th 73.6%
51.6%	46%	62%		51%	52%	47%
83.2%	83%	85%		80%	86%	82%
82.6%	83%	80%		81%	85%	84%
77.0%	78%	76%		76%	73%	82%
60.4%	61%	80%		65%	46%	50%
70.8%	81%	75%		77%	60%	61%
77.4%	79%	81%		74%	80%	73%
73.2%	77%	70%		79%	62%	78%
71.4%	63%	81%		68%	82%	63%
65.8%	76%	69%		59%	51%	74%
90.4%	91%	91%		92%	88%	90%
71.0%	74%	72%		70%	78%	61%
66.4%	83%	70%		59%	61%	59%
80.4%	91%	78%		79%	69%	85%
58.8%	62%	66%		44%	71%	51%
78.0%	83%	81%		79%	72%	75%
91.6%	89%	94%		88%	94%	93%
68.0%	81%	58%		70%	69%	62%
78.2%	79%	83%		77%	75%	77%
53.8%	70%	48%		60%	34%	57%
82.8%	77%	80%		82%	85%	90%
88.4%	86%	92%		89%	87%	88%
85.2%	90%	92%		86%	77%	81%
74.6%	73%	70%		77%	70%	83%
53.0%	49%	57%		48%	53%	58%
87.6%	93%	84%		87%	83%	91%
85.2%	85%	90%		74%	85%	92%
70.8%	72%	78%		74%	65%	65%
71.4%	75%	68%		73%	71%	70%
65.4%	75%	75%		65%	63%	49%
75.6%	75%	62%		81%	75%	85%
74.0%	80%	57%		73%	80%	80%
70.0%	70%	78%		72%	66%	64%
82.4%	89%	88%		85%	65%	85%
67.6%	64%	65%		69%	66%	74%
78.8%	77%	79%		80%	77%	81%
53.8%	54%	42%		57%	59%	57%
80.0%	72%	77%		87%	77%	87%
64.6%	71%	74%		68%	55%	55%
68.6%	69%	74%		68%	71%	61%
80.8%	87%	66%		75%	89%	87%
66.0%	72%	56%		62%	66%	74%
74.4%	84%	77%		77%	57%	77%
84.8%	88%	84%		85%	86%	81%
69.4%	73%	78%		80%	46%	70%
61.6%	55%	74%		65%	51%	63%
87.6%	82%	81%		93%	93%	89%
72.0%	64%	65%		76%	78%	77%
72.8%	85%	81%		68%	57%	73%
80.0%	78%	87%		80%	67%	88%
59.6%	60%	59%		62%	61%	56%
72.8%	80%	74%		73%	62%	75%
87.0%	88%	85%		91%	81%	90%
71.6%	75%	77%		74%	67%	65%
86.6%	87%	88%		77%	91%	90%
67.8%	69%	89%		63%	49%	69%
62.6%	70%	58%		67%	65%	53%
77.8%	79%	78%		77%	77%	78%
78.6%	84%	72%		83%	71%	83%
83.8%	86%	82%		81%	85%	85%
74.4%	79%	73%		66%	83%	71%
80.6%	73%	87%		84%	74%	85%
81.0%	76%	81%		83%	85%	80%
77.2%	75%	75%		82%	71%	83%
76.8%	75%	87%		75%	76%	71%
69.2%	70%	72%		72%	68%	64%
80.0%	85%	82%		76%	81%	76%
75.6%	75%	72%		83%	61%	87%
68.6%	72%	67%		72%	67%	65%
74.2%	90%	52%		86%	68%	75%
83.6%	92%	91%		86%	64%	85%
67.6%	68%	71%		71%	58%	70%
60.8%	55%	80%		55%	57%	57%
79.4%	70%	88%		82%	81%	76%
66.6%	70%	62%		80%	48%	73%
82.4%	82%	82%		80%	86%	82%
82.8%	85%	79%		80%	85%	85%
75.2%	73%	77%		72%	72%	82%
62.6%	67%	73%		62%	44%	67%
53.0%	61%	68%		60%	37%	39%
60.2%	78%	88%		56%	45%	34%
91.8%	97%	95%		87%	94%	86%
80.0%	74%	79%		81%	86%	80%
70.0%	77%	75%		71%	53%	74%
68.8%	64%	61%		68%	77%	74%
87.4%	86%	83%		98%	82%	88%
66.0%	72%	65%		62%	62%	69%
82.6%	79%	85%		79%	84%	86%
75.8%	78%	88%		82%	63%	68%
89.0%	88%	90%		93%	88%	86%
63.2%	66%	69%		65%	58%	58%