	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 78.5%	1st 78.8%	5th 74.8%	3rd 78.5%	6th 72.0%	4th 77.7%
65.8%	64%	61%	71%	70%	56%	73%
66.2%	74%	76%	52%	61%	74%	60%
64.7%	71%	70%	66%	59%	68%	54%
79.0%	83%	75%	72%	79%	82%	83%
85.8%	94%	88%	84%	90%	72%	87%
82.8%	73%	86%	71%	85%	93%	89%
90.7%	89%	85%	92%	94%	92%	92%
73.3%	77%	70%	57%	75%	83%	78%
76.3%	79%	91%	63%	77%	71%	77%
82.2%	82%	95%	81%	82%	76%	77%
69.0%	69%	77%	74%	72%	54%	68%
71.5%	59%	57%	86%	77%	70%	80%
81.8%	78%	95%	92%	84%	63%	79%
78.5%	82%	74%	72%	80%	81%	82%
70.7%	69%	74%	60%	68%	76%	77%
61.2%	67%	58%	65%	65%	52%	60%
85.2%	91%	89%	78%	89%	82%	82%
78.8%	88%	86%	58%	82%	85%	74%
71.7%	76%	76%	59%	78%	72%	69%
62.5%	65%	67%	73%	66%	44%	60%
80.8%	82%	85%	75%	85%	74%	84%
69.3%	78%	56%	67%	61%	67%	87%
94.3%	99%	99%	92%	83%	95%	98%
81.2%	85%	86%	78%	78%	74%	86%
80.5%	76%	93%	92%	84%	61%	77%
68.2%	60%	75%	80%	75%	46%	73%
85.0%	88%	62%	96%	91%	82%	91%
84.5%	82%	71%	96%	90%	75%	93%
92.5%	95%	96%	75%	99%	94%	96%
71.8%	66%	83%	57%	72%	84%	69%
68.3%	68%	77%	78%	69%	51%	67%
68.5%	64%	67%	72%	70%	67%	71%
75.0%	78%	80%	71%	73%	75%	73%
79.0%	81%	86%	76%	80%	77%	74%
83.7%	90%	92%	85%	88%	65%	82%
85.5%	87%	83%	75%	87%	91%	90%
74.2%	71%	78%	78%	71%	68%	79%
73.0%	81%	72%	70%	76%	62%	77%
63.2%	69%	59%	69%	66%	48%	68%
86.7%	94%	84%	89%	89%	81%	83%
82.7%	90%	85%	81%	85%	70%	85%
81.7%	82%	83%	85%	86%	77%	77%
60.0%	66%	69%	43%	61%	66%	55%
71.0%	71%	71%	76%	79%	59%	70%
89.7%	90%	95%	85%	94%	79%	95%
82.5%	90%	86%	76%	88%	80%	75%