	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 62.4%	4th 58.0%	3rd 59.0%	2nd 59.1%	5th 57.9%	6th 56.2%
48.5%	55%	52%	48%	52%	39%	45%
65.7%	78%	76%	58%	73%	51%	58%
82.0%	79%	98%	95%	79%	66%	75%
52.2%	48%	37%	59%	58%	53%	58%
41.8%	54%	13%	59%	46%	47%	32%
32.2%	44%	27%	41%	27%	27%	27%
75.3%	80%	51%	80%	82%	77%	82%
62.8%	72%	100%	51%	51%	59%	44%
66.3%	77%	32%	62%	81%	73%	73%
61.7%	70%	75%	52%	62%	64%	47%
41.8%	42%	54%	24%	49%	42%	40%
66.0%	60%	33%	70%	77%	77%	79%
46.5%	63%	77%	37%	59%	13%	30%
54.7%	53%	51%	58%	51%	59%	56%
58.7%	65%	54%	63%	54%	61%	55%
69.7%	73%	69%	72%	65%	73%	66%
50.2%	54%	38%	47%	52%	60%	50%
56.2%	63%	36%	67%	65%	48%	58%
66.2%	65%	74%	65%	62%	74%	57%
74.2%	80%	89%	71%	66%	73%	66%
54.7%	50%	45%	63%	66%	43%	61%
52.3%	68%	13%	65%	59%	57%	52%
74.3%	85%	83%	68%	59%	92%	59%
50.2%	53%	21%	62%	52%	55%	58%
56.8%	61%	58%	58%	58%	50%	56%
76.7%	85%	81%	69%	80%	60%	85%
62.5%	62%	60%	77%	55%	57%	64%
52.3%	62%	50%	46%	56%	56%	44%
62.2%	64%	63%	59%	60%	69%	58%
68.3%	60%	71%	66%	71%	71%	71%
46.3%	49%	51%	38%	48%	43%	49%
51.2%	45%	76%	34%	47%	50%	55%
55.7%	70%	48%	52%	57%	63%	44%
60.3%	67%	47%	73%	62%	50%	63%
55.7%	51%	100%	51%	51%	51%	30%
63.7%	70%	62%	64%	65%	47%	74%
67.0%	68%	57%	68%	68%	69%	72%
53.5%	39%	71%	39%	54%	77%	41%
43.7%	44%	36%	52%	40%	48%	42%
70.5%	70%	81%	59%	66%	68%	79%
47.8%	52%	33%	48%	60%	47%	47%
53.7%	63%	54%	47%	52%	58%	48%
36.8%	38%	54%	30%	40%	31%	28%
28.8%	37%	5%	59%	24%	24%	24%
70.0%	70%	73%	70%	68%	74%	65%
71.2%	66%	71%	62%	71%	71%	86%
58.8%	73%	67%	58%	44%	67%	44%
58.7%	71%	58%	51%	62%	63%	47%
65.7%	69%	74%	63%	66%	67%	55%
59.7%	63%	63%	73%	57%	46%	56%
70.2%	69%	77%	77%	72%	56%	70%
64.2%	63%	59%	67%	57%	70%	69%
89.3%	89%	92%	85%	83%	92%	95%
48.5%	51%	42%	53%	48%	50%	47%