	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 80.5%	1st 81.1%	6th 73.4%	3rd 78.3%	5th 73.9%	4th 77.1%
65.0%	78%	59%	74%	63%	64%	52%
89.2%	96%	88%	94%	86%	82%	89%
88.0%	91%	92%	89%	96%	75%	85%
74.3%	80%	78%	66%	73%	70%	79%
69.8%	78%	58%	61%	66%	71%	85%
74.8%	74%	79%	62%	79%	86%	69%
85.8%	91%	88%	64%	94%	90%	88%
60.3%	75%	100%	46%	41%	56%	44%
72.5%	68%	79%	68%	78%	70%	72%
80.8%	89%	86%	66%	85%	77%	82%
82.2%	71%	85%	85%	80%	86%	86%
81.0%	79%	70%	85%	84%	83%	85%
54.3%	63%	68%	55%	55%	43%	42%
84.2%	94%	91%	83%	83%	70%	84%
83.7%	91%	87%	79%	83%	75%	87%
89.5%	90%	96%	90%	88%	83%	90%
79.3%	84%	85%	71%	84%	78%	74%
84.2%	87%	90%	83%	86%	78%	81%
62.0%	72%	74%	59%	61%	50%	56%
81.7%	89%	92%	65%	86%	79%	79%
85.5%	92%	89%	76%	89%	75%	92%
86.7%	93%	93%	70%	90%	81%	93%
57.7%	57%	57%	62%	45%	77%	48%
82.3%	87%	73%	92%	76%	83%	83%
84.7%	90%	91%	84%	86%	69%	88%
83.3%	90%	95%	89%	83%	60%	83%
92.2%	88%	90%	96%	92%	92%	95%
79.3%	88%	90%	60%	83%	80%	75%
73.2%	81%	75%	61%	78%	78%	66%
68.5%	76%	67%	73%	66%	60%	69%
62.3%	63%	63%	53%	65%	60%	70%
73.7%	69%	72%	65%	80%	69%	87%
82.3%	81%	92%	66%	84%	79%	92%
83.8%	82%	88%	84%	85%	73%	91%
50.3%	54%	60%	53%	42%	39%	54%
88.2%	85%	90%	94%	91%	84%	85%
83.5%	87%	91%	71%	87%	86%	79%
61.5%	58%	67%	61%	58%	68%	57%
87.3%	82%	89%	87%	92%	88%	86%
83.2%	74%	88%	78%	89%	93%	77%
74.5%	74%	78%	69%	75%	81%	70%
71.0%	78%	80%	58%	67%	78%	65%
83.0%	86%	93%	78%	84%	73%	84%
78.0%	88%	69%	84%	84%	75%	68%
82.2%	84%	79%	76%	84%	85%	85%
73.8%	75%	80%	68%	76%	69%	75%
53.7%	63%	61%	52%	64%	34%	48%
68.7%	74%	71%	52%	72%	77%	66%
85.8%	85%	88%	87%	82%	84%	89%
78.5%	84%	85%	76%	80%	67%	79%
85.3%	94%	87%	93%	91%	58%	89%
87.3%	85%	85%	91%	91%	83%	89%
80.0%	74%	80%	73%	77%	88%	88%
84.2%	88%	78%	85%	89%	77%	88%