	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 63.4%	2nd 64.3%	6th 57.3%	1st 64.5%	5th 60.5%	3rd 64.0%
47.3%	55%	45%	38%	56%	41%	49%
59.7%	65%	61%	51%	58%	65%	58%
48.3%	52%	62%	42%	42%	50%	42%
73.3%	72%	74%	61%	76%	81%	76%
47.8%	52%	51%	45%	45%	48%	46%
80.0%	83%	61%	84%	84%	84%	84%
65.5%	69%	60%	68%	63%	65%	68%
56.5%	60%	46%	54%	56%	56%	67%
71.3%	71%	81%	67%	71%	71%	67%
79.2%	67%	77%	81%	82%	90%	78%
56.3%	55%	76%	55%	55%	42%	55%
48.5%	43%	39%	58%	53%	42%	56%
62.7%	73%	75%	45%	83%	42%	58%
72.2%	71%	72%	58%	78%	76%	78%
49.8%	55%	36%	39%	53%	59%	57%
32.3%	32%	35%	29%	28%	28%	42%
86.0%	84%	89%	90%	90%	73%	90%
66.7%	68%	67%	68%	66%	65%	66%
60.7%	60%	63%	55%	64%	64%	58%
48.3%	55%	49%	55%	55%	27%	49%
62.3%	60%	64%	56%	64%	63%	67%
58.8%	68%	30%	58%	57%	61%	79%
85.8%	89%	87%	82%	83%	91%	83%
47.3%	32%	68%	45%	44%	52%	43%
62.7%	73%	75%	45%	83%	42%	58%
53.8%	56%	62%	10%	67%	55%	73%
68.3%	65%	60%	67%	70%	74%	74%
71.3%	73%	62%	76%	76%	65%	76%
74.5%	81%	91%	10%	83%	91%	91%
59.7%	54%	65%	37%	57%	72%	73%
68.5%	68%	73%	68%	68%	65%	69%
58.2%	59%	57%	62%	59%	54%	58%
70.2%	66%	65%	72%	76%	76%	66%
62.7%	57%	68%	64%	60%	60%	67%
76.3%	75%	80%	82%	76%	60%	85%
91.0%	90%	90%	100%	87%	90%	89%
68.2%	65%	70%	72%	63%	71%	68%
45.3%	51%	73%	33%	47%	27%	41%
44.8%	44%	42%	48%	57%	31%	47%
69.8%	63%	76%	64%	65%	78%	73%
54.0%	61%	62%	53%	56%	39%	53%
58.8%	67%	66%	59%	56%	74%	31%
55.2%	57%	57%	52%	55%	55%	55%
65.3%	63%	65%	63%	73%	54%	74%
68.5%	73%	74%	66%	68%	61%	69%
53.5%	64%	59%	51%	59%	51%	37%