	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 66.4%	1st 67.4%	- -	3rd 63.4%	5th 58.2%	4th 61.1%
20.8%	22%	38%		12%	14%	18%
70.2%	71%	67%		71%	71%	71%
72.2%	73%	67%		74%	72%	75%
58.4%	62%	63%		48%	72%	47%
75.0%	74%	77%		81%	67%	76%
54.4%	71%	62%		51%	35%	53%
67.2%	73%	77%		60%	62%	64%
54.6%	54%	58%		63%	47%	51%
69.6%	57%	70%		64%	98%	59%
60.4%	68%	72%		64%	54%	44%
47.2%	50%	40%		51%	50%	45%
59.2%	69%	70%		40%	77%	40%
54.6%	53%	58%		60%	41%	61%
71.6%	76%	76%		81%	63%	62%
37.2%	44%	49%		23%	60%	10%
97.6%	96%	98%		98%	98%	98%
59.4%	56%	76%		50%	69%	46%
68.2%	78%	54%		68%	78%	63%
73.6%	75%	67%		74%	74%	78%
64.6%	79%	61%		66%	57%	60%
58.2%	56%	72%		59%	36%	68%
76.2%	80%	75%		75%	75%	76%
61.4%	66%	67%		44%	80%	50%
75.8%	83%	82%		79%	70%	65%
29.2%	29%	37%		25%	30%	25%
74.4%	78%	77%		79%	61%	77%
65.4%	81%	69%		61%	48%	68%
48.2%	58%	43%		54%	43%	43%
65.0%	67%	71%		60%	66%	61%
74.0%	100%	100%		60%	55%	55%
61.4%	61%	62%		61%	62%	61%
66.0%	66%	50%		71%	70%	73%
69.2%	70%	71%		70%	63%	72%
55.6%	57%	65%		60%	38%	58%
56.0%	72%	68%		51%	38%	51%
61.0%	64%	65%		65%	52%	59%
50.0%	51%	37%		52%	54%	56%
70.4%	75%	67%		73%	71%	66%
82.0%	83%	80%		80%	81%	86%
66.2%	66%	79%		63%	61%	62%
72.2%	79%	77%		67%	70%	68%
56.2%	60%	46%		63%	50%	62%
65.2%	74%	65%		65%	57%	65%
62.4%	74%	47%		68%	47%	76%
55.4%	61%	58%		72%	30%	56%
63.4%	57%	80%		76%	57%	47%
66.8%	77%	66%		66%	64%	61%
75.4%	82%	68%		80%	72%	75%
39.6%	35%	39%		52%	27%	45%
66.4%	67%	72%		73%	53%	67%
69.6%	72%	70%		72%	68%	66%
58.2%	64%	62%		53%	49%	63%
63.0%	67%	67%		61%	60%	60%
60.6%	63%	68%		56%	57%	59%
61.8%	66%	64%		68%	43%	68%
75.0%	76%	76%		86%	63%	74%
67.4%	85%	66%		74%	42%	70%
62.8%	63%	50%		63%	63%	75%
62.6%	72%	70%		70%	59%	42%
62.8%	60%	48%		72%	61%	73%
82.2%	91%	90%		63%	89%	78%
62.4%	54%	76%		58%	64%	60%
47.0%	45%	77%		37%	39%	37%
51.6%	59%	69%		45%	47%	38%
73.4%	70%	72%		77%	67%	81%
61.0%	64%	59%		58%	59%	65%
58.2%	51%	68%		55%	65%	52%
69.0%	79%	66%		72%	58%	70%
80.0%	76%	64%		80%	97%	83%
63.4%	71%	47%		65%	61%	73%
45.0%	53%	43%		46%	36%	47%
61.8%	67%	60%		61%	60%	61%
42.8%	37%	71%		38%	43%	25%
54.6%	59%	81%		46%	41%	46%
64.8%	67%	62%		60%	62%	73%
62.4%	56%	59%		61%	71%	65%
89.0%	89%	89%		89%	89%	89%
41.2%	30%	70%		32%	38%	36%
56.6%	61%	52%		71%	28%	71%
54.8%	66%	81%		73%	10%	44%
77.2%	69%	100%		100%	73%	44%
82.8%	83%	77%		82%	78%	94%
78.2%	79%	76%		79%	76%	81%
35.6%	31%	47%		43%	22%	35%
52.0%	49%	78%		47%	35%	51%
74.4%	74%	75%		79%	61%	83%
71.0%	77%	79%		71%	58%	70%
57.8%	56%	79%		51%	52%	51%
79.4%	85%	98%		74%	73%	67%
87.8%	91%	88%		81%	91%	88%
75.6%	86%	88%		78%	48%	78%