	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 65.6%	3rd 62.7%	5th 58.5%	1st 66.6%	6th 57.2%	4th 61.2%
57.5%	54%	48%	54%	77%	62%	50%
42.0%	51%	56%	28%	40%	41%	36%
51.3%	61%	72%	34%	55%	37%	49%
100.0%	100%	100%	100%	100%	100%	100%
40.0%	32%	43%	37%	37%	42%	49%
56.5%	37%	63%	64%	51%	66%	58%
73.2%	70%	69%	80%	79%	68%	73%
52.0%	47%	54%	47%	58%	56%	50%
67.0%	76%	44%	72%	82%	67%	61%
62.7%	76%	67%	60%	56%	52%	65%
71.8%	79%	79%	67%	66%	79%	61%
44.0%	47%	34%	53%	58%	27%	45%
67.8%	72%	88%	82%	72%	26%	67%
100.0%	100%	100%	100%	100%	100%	100%
65.3%	72%	55%	46%	73%	73%	73%
53.0%	56%	41%	45%	66%	59%	51%
75.0%	76%	73%	76%	79%	73%	73%
68.8%	66%	68%	64%	73%	69%	73%
66.8%	72%	71%	62%	73%	58%	65%
50.8%	61%	59%	50%	55%	37%	43%
52.0%	65%	57%	47%	61%	32%	50%
58.3%	62%	48%	49%	72%	54%	65%
81.0%	87%	83%	87%	73%	83%	73%
50.5%	58%	33%	46%	54%	57%	55%
67.8%	72%	88%	82%	72%	26%	67%
65.8%	74%	71%	70%	69%	53%	58%
51.2%	56%	36%	49%	50%	51%	65%
60.3%	70%	51%	60%	73%	50%	58%
77.8%	86%	100%	10%	100%	90%	81%
59.8%	72%	56%	35%	56%	84%	56%
51.8%	51%	33%	54%	66%	45%	62%
76.0%	73%	90%	77%	78%	72%	66%
65.2%	78%	70%	71%	62%	41%	69%
61.5%	60%	45%	63%	65%	68%	68%
51.2%	46%	56%	55%	57%	44%	49%
59.0%	50%	54%	65%	50%	70%	65%
64.2%	73%	60%	62%	77%	61%	52%
48.7%	48%	44%	45%	48%	52%	55%
47.5%	61%	49%	34%	55%	43%	43%
69.0%	76%	74%	55%	74%	77%	58%
62.8%	76%	73%	64%	80%	28%	56%
45.3%	36%	63%	52%	45%	41%	35%
59.8%	75%	67%	38%	57%	70%	52%
63.8%	70%	65%	59%	74%	42%	73%
55.3%	62%	53%	60%	57%	40%	60%
78.7%	76%	80%	81%	90%	65%	80%