	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 68.7%	3rd 66.5%	- -	2nd 68.6%	5th 63.4%	4th 65.7%
33.6%	34%	48%		30%	29%	27%
70.6%	72%	62%		72%	78%	69%
75.4%	72%	78%		77%	78%	72%
68.2%	68%	67%		73%	72%	61%
62.6%	59%	62%		67%	58%	67%
56.2%	59%	45%		60%	57%	60%
76.2%	77%	72%		80%	67%	85%
57.8%	66%	61%		60%	50%	52%
81.4%	81%	83%		80%	99%	64%
69.0%	81%	73%		67%	52%	72%
84.0%	81%	95%		87%	85%	72%
75.0%	73%	75%		81%	66%	80%
65.0%	72%	63%		65%	60%	65%
74.6%	73%	70%		75%	91%	64%
57.4%	61%	68%		38%	73%	47%
78.8%	56%	66%		100%	87%	85%
58.6%	61%	57%		57%	61%	57%
71.0%	74%	62%		73%	73%	73%
70.2%	70%	53%		83%	70%	75%
49.6%	64%	40%		66%	12%	66%
56.8%	57%	57%		57%	54%	59%
65.2%	67%	69%		55%	64%	71%
58.4%	48%	58%		66%	52%	68%
59.4%	59%	54%		62%	58%	64%
34.0%	23%	47%		37%	26%	37%
74.2%	78%	70%		72%	71%	80%
64.8%	64%	60%		79%	56%	65%
62.0%	62%	59%		63%	61%	65%
51.6%	51%	60%		52%	51%	44%
70.8%	71%	100%		67%	73%	43%
56.2%	54%	61%		71%	32%	63%
57.8%	65%	44%		57%	58%	65%
78.0%	84%	68%		74%	86%	78%
75.8%	84%	76%		78%	67%	74%
71.2%	75%	77%		66%	73%	65%
55.0%	64%	53%		59%	49%	50%
65.6%	68%	66%		70%	63%	61%
66.4%	65%	51%		72%	69%	75%
68.0%	70%	67%		71%	66%	66%
55.8%	59%	52%		63%	62%	43%
71.8%	85%	42%		80%	84%	68%
58.6%	64%	52%		60%	52%	65%
69.8%	76%	78%		74%	45%	76%
74.0%	73%	77%		74%	72%	74%
67.2%	77%	74%		64%	57%	64%
49.2%	51%	60%		44%	46%	45%
70.2%	73%	69%		69%	70%	70%
63.8%	62%	57%		70%	59%	71%
64.4%	62%	64%		71%	56%	69%
66.6%	71%	72%		64%	66%	60%
63.2%	64%	70%		56%	62%	64%
55.2%	57%	56%		53%	54%	56%
63.2%	67%	66%		65%	65%	53%
79.0%	81%	81%		77%	80%	76%
67.2%	64%	60%		81%	54%	77%
64.6%	66%	100%		62%	36%	59%
66.2%	85%	60%		77%	57%	52%
70.8%	74%	70%		75%	66%	69%
85.0%	84%	82%		85%	87%	87%
82.6%	78%	78%		91%	83%	83%
57.8%	62%	61%		52%	63%	51%
64.0%	58%	67%		65%	63%	67%
71.4%	76%	58%		76%	66%	81%
76.4%	82%	73%		72%	81%	74%
52.2%	50%	56%		54%	51%	50%
59.0%	54%	58%		58%	63%	62%
80.6%	81%	67%		93%	72%	90%
61.6%	65%	58%		65%	56%	64%
74.0%	76%	77%		72%	73%	72%
70.6%	87%	56%		76%	73%	61%
77.8%	87%	84%		77%	62%	79%
49.2%	57%	55%		65%	13%	56%
56.4%	59%	57%		59%	52%	55%
54.4%	56%	50%		60%	53%	53%
55.8%	68%	55%		71%	22%	63%
72.6%	73%	61%		71%	78%	80%
82.6%	78%	78%		91%	83%	83%
57.0%	45%	59%		61%	61%	59%
72.4%	83%	75%		69%	70%	65%
60.2%	66%	73%		66%	52%	44%
65.4%	69%	100%		59%	55%	44%
88.2%	98%	84%		93%	82%	84%
69.8%	67%	75%		60%	75%	72%
69.0%	73%	68%		67%	70%	67%
71.8%	77%	64%		81%	65%	72%
59.2%	65%	65%		55%	60%	51%
79.0%	83%	81%		62%	86%	83%
67.4%	71%	65%		62%	71%	68%
86.6%	85%	92%		96%	79%	81%
91.2%	88%	94%		93%	90%	91%
69.0%	78%	65%		65%	68%	69%