	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 73.9%	1st 74.0%	5th 65.9%	3rd 72.9%	6th 65.8%	4th 71.8%
43.5%	49%	50%	44%	40%	27%	51%
57.3%	64%	64%	47%	52%	63%	54%
59.8%	69%	68%	64%	60%	47%	51%
72.8%	76%	79%	58%	74%	74%	76%
78.5%	81%	84%	81%	69%	78%	78%
74.7%	78%	78%	78%	72%	79%	63%
78.5%	84%	83%	77%	76%	76%	75%
68.5%	77%	64%	55%	75%	73%	67%
70.8%	68%	81%	65%	79%	64%	68%
74.8%	81%	79%	71%	77%	72%	69%
64.8%	64%	80%	69%	64%	49%	63%
66.2%	64%	51%	87%	71%	50%	74%
65.3%	65%	66%	52%	85%	46%	78%
72.0%	75%	78%	57%	73%	73%	76%
68.2%	74%	61%	64%	67%	73%	70%
52.8%	57%	58%	44%	59%	44%	55%
81.0%	85%	82%	75%	88%	86%	70%
77.0%	76%	79%	64%	81%	81%	81%
74.8%	76%	87%	62%	78%	72%	74%
61.7%	62%	82%	79%	61%	33%	53%
66.3%	61%	67%	62%	67%	69%	72%
66.2%	80%	51%	57%	65%	63%	81%
92.2%	92%	93%	85%	85%	98%	100%
86.0%	88%	75%	83%	88%	90%	92%
59.2%	58%	60%	46%	79%	40%	72%
61.7%	56%	60%	74%	68%	55%	57%
73.2%	74%	59%	72%	77%	76%	81%
71.0%	76%	61%	85%	66%	58%	80%
77.0%	86%	96%	10%	89%	91%	90%
60.8%	67%	71%	46%	54%	68%	59%
49.0%	57%	52%	46%	48%	38%	53%
68.5%	68%	74%	61%	70%	66%	72%
76.7%	81%	89%	72%	74%	74%	70%
75.0%	80%	91%	71%	69%	66%	73%
83.8%	87%	81%	85%	90%	79%	81%
82.0%	87%	90%	57%	88%	85%	85%
70.5%	74%	74%	71%	67%	63%	74%
74.5%	77%	75%	72%	73%	69%	81%
64.0%	62%	73%	76%	72%	40%	61%
75.0%	78%	83%	80%	79%	63%	67%
79.2%	87%	84%	80%	81%	69%	74%
78.5%	76%	74%	77%	79%	76%	89%
57.5%	61%	66%	42%	66%	57%	53%
77.3%	82%	78%	82%	79%	64%	79%
86.3%	91%	93%	82%	95%	71%	86%
78.2%	88%	81%	63%	84%	77%	76%