	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 68.3%	5th 63.6%	1st 76.0%	3rd 67.3%	6th 62.8%	4th 66.5%
40.6%	36%	59%		38%	32%	38%
60.4%	64%	71%		61%	49%	57%
63.8%	65%	78%		63%	54%	59%
72.0%	71%	74%		68%	78%	69%
81.0%	88%	80%		80%	81%	76%
57.8%	76%	35%		66%	57%	55%
62.2%	64%	40%		68%	68%	71%
68.8%	74%	65%		70%	64%	71%
69.8%	58%	90%		65%	78%	58%
77.8%	84%	100%		68%	60%	77%
67.8%	61%	68%		72%	69%	69%
54.0%	63%	61%		39%	57%	50%
82.6%	83%	94%		80%	77%	79%
52.6%	61%	48%		65%	42%	47%
54.2%	61%	63%		35%	78%	34%
57.0%	61%	44%		64%	52%	64%
52.6%	61%	29%		61%	56%	56%
51.2%	73%	46%		61%	32%	44%
79.6%	84%	71%		85%	78%	80%
60.4%	71%	71%		57%	46%	57%
76.2%	82%	64%		79%	81%	75%
62.6%	76%	24%		69%	68%	76%
55.6%	70%	65%		58%	30%	55%
72.0%	74%	70%		79%	61%	76%
22.8%	19%	32%		21%	19%	23%
72.8%	85%	47%		59%	89%	84%
81.8%	89%	99%		63%	78%	80%
76.8%	71%	92%		71%	80%	70%
65.8%	70%	55%		68%	67%	69%
66.6%	67%	80%		64%	64%	58%
75.0%	80%	80%		80%	69%	66%
70.2%	75%	45%		79%	72%	80%
70.2%	68%	71%		77%	69%	66%
67.8%	63%	70%		81%	55%	70%
68.8%	71%	50%		76%	68%	79%
69.4%	77%	71%		72%	55%	72%
68.8%	75%	24%		84%	77%	84%
66.0%	76%	46%		80%	56%	72%
74.0%	76%	93%		71%	63%	67%
65.6%	68%	85%		62%	56%	57%
73.2%	78%	77%		61%	83%	67%
68.8%	81%	30%		85%	79%	69%
66.2%	57%	85%		66%	55%	68%
64.4%	65%	67%		62%	63%	65%
51.8%	59%	43%		61%	42%	54%
60.0%	59%	77%		64%	40%	60%
74.2%	82%	40%		90%	68%	91%
47.8%	41%	30%		52%	64%	52%
83.2%	75%	82%		90%	78%	91%
41.6%	39%	31%		45%	39%	54%
46.4%	49%	35%		46%	51%	51%
64.2%	65%	70%		64%	61%	61%
74.6%	80%	75%		67%	66%	85%
60.4%	69%	62%		60%	53%	58%
80.2%	72%	72%		92%	71%	94%
64.0%	58%	90%		68%	36%	68%
48.2%	73%	40%		53%	27%	48%
71.8%	72%	69%		73%	82%	63%
44.0%	48%	38%		48%	41%	45%
70.2%	83%	55%		73%	61%	79%
74.2%	85%	80%		64%	84%	58%
70.4%	69%	69%		69%	70%	75%
51.8%	55%	25%		61%	65%	53%
69.8%	67%	52%		76%	76%	78%
77.8%	83%	67%	76%	76%	73%	92%
60.8%	74%	22%		60%	77%	71%
67.6%	70%	64%		59%	74%	71%
85.0%	89%	74%		79%	100%	83%
75.2%	82%	99%		70%	64%	61%
54.4%	0%	61%		73%	64%	74%
54.8%	64%	64%		60%	30%	56%
68.8%	73%	65%		68%	65%	73%
38.0%	34%	58%		36%	23%	39%
76.6%	76%	69%		80%	84%	74%
73.0%	80%	69%		70%	69%	77%
85.4%	99%	79%		91%	79%	79%
100.0%	100%	100%		100%	100%	100%
56.4%	51%	76%		52%	50%	53%
71.6%	68%	60%		92%	58%	80%
63.5%	66%	72%		64%		52%
67.6%	71%	100%		58%	58%	51%
74.4%	71%	66%		73%	86%	76%
52.8%	60%	31%		58%	58%	57%
57.4%	53%	66%		63%	41%	64%
75.6%	74%	78%		72%	81%	73%
60.2%	58%	48%		65%	58%	72%
73.0%	81%	56%		73%	71%	84%
50.4%	42%	65%		47%	49%	49%
75.0%	85%	80%		78%	66%	66%
74.6%	71%	84%		78%	71%	69%
70.2%	72%	68%		76%	60%	75%