	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 60.0%	1st 61.6%	6th 54.5%	2nd 60.4%	5th 55.4%	3rd 60.3%
38.7%	33%	33%	46%	42%	33%	45%
25.7%	29%	29%	16%	20%	29%	31%
56.7%	67%	63%	51%	51%	56%	52%
72.8%	72%	75%	64%	68%	82%	76%
54.5%	56%	66%	32%	41%	72%	60%
53.8%	52%	55%	37%	65%	61%	53%
58.0%	57%	63%	60%	56%	58%	54%
53.0%	55%	26%	52%	60%	60%	65%
38.0%	43%	55%	29%	34%	35%	32%
87.8%	83%	89%	83%	86%	86%	100%
73.3%	82%	96%	70%	75%	47%	70%
57.8%	54%	58%	74%	56%	46%	59%
67.3%	78%	77%	61%	78%	48%	62%
75.7%	74%	81%	64%	73%	81%	81%
49.0%	43%	46%	46%	41%	61%	57%
32.0%	30%	41%	29%	41%	10%	41%
70.7%	81%	60%	54%	70%	81%	78%
61.3%	66%	72%	40%	56%	72%	62%
44.0%	50%	53%	25%	42%	49%	45%
47.5%	50%	54%	54%	52%	36%	39%
81.0%	83%	84%	60%	87%	87%	85%
47.7%	58%	27%	48%	43%	43%	67%
94.8%	98%	100%	97%	89%	88%	97%
58.0%	56%	64%	52%	59%	58%	59%
66.3%	79%	76%	58%	78%	46%	61%
65.3%	61%	76%	67%	69%	50%	69%
53.2%	58%	68%	47%	41%	49%	56%
70.7%	69%	70%	78%	76%	55%	76%
65.3%	80%	77%	34%	80%	57%	64%
33.7%	32%	39%	12%	41%	41%	37%
37.0%	30%	40%	45%	40%	27%	40%
57.7%	59%	53%	61%	58%	54%	61%
73.8%	65%	71%	76%	78%	78%	75%
52.3%	51%	60%	48%	51%	50%	54%
76.0%	78%	74%	90%	74%	66%	74%
94.0%	92%	93%	94%	96%	95%	94%
65.2%	59%	73%	65%	60%	62%	72%
35.6%	34%	48%	29%		31%	36%
48.7%	50%	53%	56%	59%	28%	46%
60.0%	69%	55%	55%	63%	55%	63%
58.8%	66%	56%	51%	55%	64%	61%
55.3%	54%	43%	55%	65%	54%	61%
41.4%	49%	47%	30%		53%	28%
51.3%	46%	53%	61%	55%	45%	48%
74.5%	73%	79%	91%	70%	62%	72%
57.8%	58%	62%	62%	62%	46%	57%