	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 74.4%	1st 74.5%	6th 66.1%	4th 71.9%	3rd 73.2%	5th 70.1%
69.7%	79%	67%	75%	68%	72%	57%
86.2%	94%	80%	82%	90%	79%	92%
87.0%	81%	81%	90%	86%	95%	89%
75.2%	79%	78%	70%	77%	69%	78%
59.3%	66%	43%	61%	50%	68%	68%
66.2%	66%	67%	55%	72%	68%	69%
77.7%	82%	83%	64%	83%	82%	72%
61.5%	76%	100%	46%	44%	59%	44%
68.5%	71%	73%	60%	71%	63%	73%
71.0%	73%	76%	64%	69%	73%	71%
74.7%	65%	81%	69%	76%	78%	79%
70.5%	71%	56%	73%	73%	72%	78%
54.0%	68%	84%	10%	66%	46%	50%
79.0%	80%	80%	80%	78%	77%	79%
76.5%	86%	79%	71%	76%	70%	77%
85.5%	91%	83%	85%	87%	80%	87%
73.7%	69%	70%	75%	70%	85%	73%
90.0%	94%	85%	91%	91%	88%	91%
48.3%	62%	49%	40%	43%	48%	48%
78.2%	87%	88%	64%	78%	85%	67%
81.7%	85%	89%	67%	88%	78%	83%
84.5%	83%	91%	73%	90%	85%	85%
49.3%	54%	53%	58%	37%	57%	37%
70.3%	76%	57%	70%	72%	74%	73%
83.5%	87%	84%	87%	81%	72%	90%
80.3%	86%	84%	75%	84%	69%	84%
78.5%	75%	73%	82%	83%	79%	79%
62.3%	75%	73%	48%	63%	63%	52%
69.2%	77%	80%	48%	74%	74%	62%
64.5%	74%	64%	59%	65%	65%	60%
60.7%	62%	70%	46%	71%	57%	58%
56.2%	51%	49%	49%	59%	67%	62%
74.0%	67%	88%	54%	72%	88%	75%
74.0%	78%	75%	68%	79%	66%	78%
38.7%	30%	35%	32%	30%	65%	40%
77.7%	59%	84%	84%	73%	93%	73%
75.7%	78%	84%	66%	77%	83%	66%
51.2%	47%	47%	55%	49%	61%	48%
72.0%	70%	66%	79%	73%	72%	72%
77.3%	69%	74%	82%	77%	94%	68%
65.5%	57%	86%	60%	60%	77%	53%
72.8%	85%	81%	53%	73%	82%	63%
73.3%	67%	89%	66%	72%	76%	70%
80.2%	82%	68%	93%	90%	71%	77%
85.7%	89%	89%	75%	86%	97%	78%
71.0%	77%	79%	60%	63%	68%	79%
49.3%	74%	58%	41%	43%	36%	44%
60.2%	66%	66%	44%	62%	71%	52%
87.3%	93%	98%	80%	80%	94%	79%
72.8%	82%	81%	75%	69%	56%	74%
75.0%	79%	78%	78%	76%	63%	76%
79.7%	80%	79%	77%	85%	80%	77%
84.0%	80%	80%	79%	85%	89%	91%
80.3%	84%	66%	81%	93%	73%	85%