	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 70.9%	3rd 69.2%	6th 47.0%	1st 71.4%	5th 63.6%	4th 66.9%
78.2%	84%	76%		76%	81%	74%
49.2%	55%	64%		29%	57%	41%
51.0%	61%	57%		57%	40%	40%
94.0%	94%	94%		94%	94%	94%
68.4%	59%	71%		59%	73%	80%
54.6%	35%	62%		52%	57%	67%
82.6%	88%	90%		79%	80%	76%
44.8%	47%	51%	47%	47%	34%	43%
64.0%	58%	88%		77%	57%	40%
69.0%	72%	80%		69%	58%	66%
70.8%	77%	88%		67%	61%	61%
65.4%	71%	56%		75%	58%	67%
73.0%	81%	95%		79%	47%	63%
94.0%	94%	94%		94%	94%	94%
61.4%	61%	58%		64%	61%	63%
85.0%	79%	79%		93%	79%	95%
70.6%	69%	71%		69%	69%	75%
74.4%	79%	67%		81%	65%	80%
52.2%	61%	51%		50%	45%	54%
68.6%	76%	73%		81%	50%	63%
51.0%	53%	59%		51%	43%	49%
59.8%	73%	37%		78%	47%	64%
89.4%	92%	87%		100%	81%	87%
58.2%	61%	62%		54%	48%	66%
63.0%	82%	71%		69%	38%	55%
63.4%	61%	72%		66%	52%	66%
68.8%	80%	55%		67%	67%	75%
53.0%	72%	0%		73%	56%	64%
88.2%	83%	88%		82%	94%	94%
73.8%	79%	69%		74%	72%	75%
79.4%	79%	81%		81%	81%	75%
74.2%	74%	76%		81%	74%	66%
66.0%	64%	53%		74%	73%	66%
62.4%	64%	70%		60%	50%	68%
80.6%	75%	81%		85%	85%	77%
75.6%	78%	81%		74%	72%	73%
79.8%	81%	71%		92%	90%	65%
59.8%	64%	79%		65%	41%	50%
54.6%	57%	53%		66%	47%	50%
60.2%	61%	56%		72%	55%	57%
71.4%	81%	69%		69%	69%	69%
75.2%	82%	67%		80%	80%	67%
53.2%	55%	70%		49%	41%	51%
67.2%	61%	64%		71%	69%	71%
79.8%	71%	80%		90%	78%	80%
66.8%	77%	65%		68%	62%	62%