	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 72.6%	1st 74.5%	6th 61.0%	3rd 71.3%	5th 69.0%	4th 70.3%
69.2%	76%	89%	47%	68%	67%	68%
77.3%	72%	61%	73%	78%	93%	87%
70.7%	66%	83%	71%	70%	68%	66%
49.7%	43%	56%	48%	48%	37%	66%
86.2%	87%	78%	85%	88%	91%	88%
71.3%	77%	81%	53%	71%	79%	67%
85.2%	85%	87%	81%	80%	91%	87%
46.8%	52%	64%	21%	46%	52%	46%
74.3%	77%	75%	53%	81%	80%	80%
44.2%	45%	50%	46%	48%	28%	48%
83.8%	85%	83%	82%	79%	87%	87%
42.8%	49%	50%	30%	50%	28%	50%
72.2%	72%	85%	57%	70%	78%	71%
85.7%	85%	81%	87%	89%	77%	95%
84.7%	94%	86%	72%	87%	82%	87%
67.3%	74%	81%	50%	67%	66%	66%
55.3%	62%	65%	46%	53%	60%	46%
52.8%	59%	60%	34%	56%	58%	50%
62.8%	72%	59%	43%	65%	68%	70%
78.8%	77%	81%	86%	79%	79%	71%
70.2%	78%	80%	43%	75%	82%	63%
68.7%	78%	82%	48%	68%	68%	68%
65.3%	68%	69%	56%	79%	50%	70%
74.8%	71%	83%	72%	74%	75%	74%
82.8%	89%	80%	83%	84%	78%	83%
69.2%	71%	76%	59%	73%	66%	70%
70.3%	76%	81%	57%	67%	79%	62%
62.0%	68%	84%	43%	59%	67%	51%
47.5%	56%	54%	28%	65%	30%	52%
64.8%	66%	86%	47%	74%	58%	58%
73.7%	68%	68%	88%	68%	68%	82%
75.0%	80%	62%	75%	75%	78%	80%
70.7%	66%	84%	70%	70%	68%	66%
78.2%	77%	82%	76%	80%	80%	74%
48.0%	57%	31%	40%	48%	48%	64%
70.5%	77%	68%	64%	76%	67%	71%
86.3%	86%	92%	90%	90%	73%	87%
86.2%	87%	85%	83%	82%	93%	87%
61.5%	69%	72%	49%	62%	66%	51%
88.2%	83%	98%	88%	92%	85%	83%
73.5%	73%	83%	71%	72%	71%	71%
74.0%	81%	73%	55%	76%	76%	83%
79.2%	89%	77%	72%	86%	74%	77%