	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 73.3%	3rd 72.1%	5th 66.3%	1st 73.3%	6th 64.8%	4th 71.6%
79.5%	81%	82%	76%	79%	82%	77%
65.5%	68%	69%	56%	64%	68%	68%
46.7%	59%	57%	32%	54%	36%	42%
100.0%	100%	100%	100%	100%	100%	100%
74.5%	82%	73%	76%	74%	74%	68%
76.2%	54%	86%	76%	75%	83%	83%
72.2%	70%	75%	73%	70%	70%	75%
43.0%	46%	72%	28%	45%	27%	40%
64.5%	59%	96%	61%	72%	48%	51%
78.0%	91%	82%	64%	84%	71%	76%
76.5%	84%	82%	76%	81%	62%	74%
53.7%	60%	50%	50%	65%	43%	54%
72.2%	84%	76%	84%	84%	39%	66%
100.0%	100%	100%	100%	100%	100%	100%
56.8%	66%	45%	37%	70%	63%	60%
81.7%	82%	77%	85%	85%	79%	82%
70.3%	67%	73%	73%	68%	73%	68%
73.0%	76%	68%	70%	74%	74%	76%
51.5%	58%	52%	43%	52%	52%	52%
69.2%	76%	74%	60%	82%	63%	60%
70.0%	69%	60%	74%	73%	65%	79%
67.7%	72%	64%	80%	82%	39%	69%
89.5%	97%	88%	71%	83%	99%	99%
67.8%	69%	68%	60%	70%	68%	72%
72.7%	83%	74%	84%	84%	42%	69%
64.3%	64%	69%	69%	78%	41%	65%
73.2%	82%	61%	83%	77%	57%	79%
67.5%	73%	67%	66%	72%	56%	71%
76.3%	87%	98%	10%	85%	89%	89%
57.7%	63%	51%	53%	59%	54%	66%
76.8%	76%	81%	77%	75%	75%	77%
59.5%	58%	61%	55%	61%	59%	63%
72.5%	80%	72%	63%	89%	53%	78%
68.7%	65%	72%	63%	70%	71%	71%
75.3%	82%	70%	73%	65%	80%	82%
86.0%	84%	89%	89%	79%	88%	87%
81.8%	81%	82%	84%	77%	79%	88%
50.7%	53%	44%	48%	50%	55%	54%
61.3%	67%	66%	50%	69%	55%	61%
68.8%	72%	63%	63%	76%	63%	76%
74.8%	76%	78%	76%	80%	65%	74%
64.3%	59%	65%	66%	65%	67%	64%
51.7%	55%	50%	46%	51%	54%	54%
80.0%	83%	87%	74%	80%	65%	91%
78.3%	78%	83%	83%	65%	82%	79%
69.0%	79%	66%	70%	79%	54%	66%