	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 74.8%	1st 78.5%	6th 64.3%	3rd 73.5%	5th 65.8%	4th 73.2%
51.2%	46%	56%	48%	53%	46%	58%
59.8%	69%	73%	41%	56%	63%	57%
53.2%	63%	69%	48%	45%	47%	47%
69.8%	74%	67%	59%	71%	73%	75%
76.8%	80%	85%	64%	77%	76%	79%
74.0%	66%	88%	71%	74%	80%	65%
84.3%	81%	85%	84%	85%	86%	85%
69.0%	75%	65%	57%	72%	78%	67%
63.8%	66%	85%	57%	60%	49%	66%
79.7%	84%	89%	75%	79%	75%	76%
72.5%	70%	93%	74%	72%	54%	72%
70.7%	70%	81%	78%	66%	54%	75%
77.2%	92%	99%	54%	88%	49%	81%
68.5%	73%	69%	57%	69%	71%	72%
68.7%	68%	67%	60%	70%	72%	75%
57.7%	58%	74%	46%	57%	51%	60%
72.3%	84%	76%	52%	70%	84%	68%
77.7%	84%	84%	57%	81%	81%	79%
71.7%	79%	81%	59%	74%	70%	67%
63.8%	67%	75%	70%	69%	44%	58%
69.7%	68%	72%	64%	71%	68%	75%
64.2%	75%	56%	53%	62%	58%	81%
93.8%	99%	97%	86%	86%	99%	96%
84.2%	79%	93%	81%	85%	77%	90%
70.7%	86%	92%	48%	81%	43%	74%
66.3%	56%	75%	88%	70%	39%	70%
81.0%	82%	71%	75%	84%	86%	88%
79.7%	81%	83%	87%	84%	61%	82%
78.0%	86%	90%	10%	90%	97%	95%
61.0%	69%	78%	31%	55%	68%	65%
51.8%	46%	56%	52%	57%	47%	53%
68.5%	69%	70%	71%	72%	62%	67%
74.0%	76%	75%	72%	75%	73%	73%
68.2%	67%	92%	68%	59%	56%	67%
81.2%	87%	77%	86%	91%	65%	81%
82.0%	82%	88%	61%	89%	87%	85%
75.3%	80%	79%	74%	74%	65%	80%
73.0%	79%	76%	71%	75%	67%	70%
65.7%	66%	76%	75%	77%	34%	66%
70.2%	79%	70%	65%	76%	65%	66%
75.0%	85%	79%	61%	75%	74%	76%
75.5%	75%	77%	81%	84%	50%	86%
59.5%	69%	75%	36%	62%	62%	53%
75.5%	69%	77%	83%	80%	64%	80%
89.3%	94%	94%	85%	95%	76%	92%
81.7%	88%	80%	82%	82%	83%	75%