	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 72.7%	1st 75.3%	6th 61.1%	3rd 70.8%	5th 68.5%	4th 70.4%
71.3%	76%	87%	47%	68%	73%	77%
77.2%	71%	61%	73%	78%	93%	87%
70.5%	66%	83%	70%	70%	68%	66%
50.8%	50%	56%	48%	48%	37%	66%
84.0%	87%	78%	73%	87%	91%	88%
69.3%	77%	82%	56%	71%	63%	67%
86.2%	85%	90%	81%	91%	91%	79%
45.8%	49%	60%	22%	46%	52%	46%
75.8%	77%	84%	53%	81%	80%	80%
42.3%	45%	50%	41%	42%	28%	48%
85.0%	85%	88%	82%	79%	89%	87%
42.3%	51%	50%	30%	45%	28%	50%
70.2%	72%	72%	57%	71%	78%	71%
85.0%	85%	79%	87%	87%	77%	95%
86.2%	94%	91%	76%	87%	82%	87%
66.3%	73%	81%	50%	67%	61%	66%
52.2%	62%	65%	46%	48%	46%	46%
55.3%	59%	70%	34%	58%	58%	53%
62.0%	72%	63%	53%	64%	68%	52%
83.7%	77%	87%	86%	86%	86%	80%
70.2%	78%	80%	41%	75%	84%	63%
68.2%	75%	82%	48%	68%		68%
61.3%	68%	79%	56%	63%	32%	70%
74.3%	71%	80%	72%	74%	75%	74%
83.2%	93%	80%	83%	85%	75%	83%
69.7%	70%	76%	54%	73%	75%	70%
69.8%	76%	81%	57%	61%	79%	65%
62.4%	67%	84%	43%	67%		51%
49.7%	56%	71%	28%	61%	30%	52%
63.7%	66%	79%	56%	65%	58%	58%
72.7%	68%	68%	88%	69%	61%	82%
74.8%	80%	61%	75%	75%	78%	80%
70.2%	66%	80%	71%	70%	68%	66%
76.8%	76%	82%	75%	74%	80%	74%
51.0%	57%	31%	42%	54%	48%	74%
71.6%	79%	68%	64%	76%		71%
85.7%	86%	88%	90%	86%	77%	87%
86.3%	86%	83%	83%	86%	93%	87%
61.8%	69%	69%	50%	65%	67%	51%
87.5%	83%	98%	88%	88%	85%	83%
74.0%	73%	83%	71%	72%		71%
75.7%	81%	78%	55%	78%	83%	79%
79.3%	89%	78%	72%	86%	74%	77%