	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 66.9%	3rd 66.2%	6th 62.4%	1st 67.7%	5th 64.7%	4th 65.7%
73.5%	71%	77%	65%	72%	77%	79%
68.2%	58%	84%	58%	67%	75%	67%
70.7%	91%	83%	58%	71%	61%	60%
100.0%	100%	100%	100%	100%	100%	100%
85.8%	84%	88%	84%	79%	88%	92%
53.2%	38%	56%	55%	56%	55%	59%
76.7%	79%	92%	72%	75%	78%	64%
36.2%	36%	70%	22%	32%	22%	35%
50.5%	63%	51%	48%	64%	45%	32%
72.3%	73%	70%	62%	89%	69%	71%
62.7%	70%	76%	60%	60%	60%	50%
47.8%	51%	41%	53%	56%	34%	52%
77.0%	66%	70%	94%	66%	81%	85%
100.0%	100%	100%	100%	100%	100%	100%
61.3%	69%	55%	52%	65%	65%	62%
60.5%	58%	62%	62%	67%	62%	52%
69.2%	70%	70%	65%	70%	70%	70%
83.8%	82%	77%	78%	90%	87%	89%
69.5%	70%	68%	71%	73%	60%	75%
44.3%	62%	44%	43%	50%	31%	36%
63.7%	69%	48%	64%	67%	69%	65%
76.2%	81%	26%	90%	84%	84%	92%
93.2%	95%	100%	79%	92%	93%	100%
43.5%	42%	56%	37%	42%	46%	38%
77.0%	66%	70%	94%	66%	81%	85%
48.2%	50%	43%	53%	52%	46%	45%
37.8%	40%	14%	32%	41%	50%	50%
63.3%	72%	45%	68%	75%	54%	66%
79.3%	87%	100%	10%	85%	100%	94%
47.5%	47%	54%	41%	51%	46%	46%
75.7%	79%	77%	75%	77%	77%	69%
69.3%	65%	70%	68%	73%	72%	68%
68.5%	67%	72%	57%	79%	70%	66%
58.7%	56%	66%	59%	54%	54%	63%
49.2%	47%	56%	47%	49%	49%	47%
63.0%	61%	65%	69%	55%	61%	67%
53.5%	54%	41%	52%	62%	58%	54%
41.0%	45%	50%	37%	36%	42%	36%
50.3%	51%	51%	47%	62%	43%	48%
84.3%	78%	90%	92%	78%	84%	84%
72.7%	79%	76%	79%	70%	62%	70%
65.7%	70%	69%	71%	66%	58%	60%
66.7%	66%	71%	58%	75%	57%	73%
63.7%	68%	63%	55%	71%	64%	61%
67.2%	70%	62%	69%	73%	62%	67%
75.5%	81%	78%	66%	77%	73%	78%