	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 80.9%	2nd 80.6%	6th 73.3%	3rd 78.7%	5th 74.3%	4th 76.2%
65.2%	78%	59%	75%	62%	64%	53%
89.8%	96%	85%	94%	88%	82%	94%
88.0%	91%	92%	89%	97%	74%	85%
74.0%	80%	79%	67%	70%	73%	75%
70.5%	78%	58%	61%	70%	74%	82%
72.7%	74%	79%	54%	79%	81%	69%
86.7%	96%	85%	67%	93%	92%	87%
59.5%	75%	93%	46%	44%	55%	44%
73.2%	68%	80%	68%	81%	70%	72%
82.5%	89%	86%	66%	84%	84%	86%
81.2%	75%	85%	78%	79%	87%	83%
80.7%	79%	69%	86%	84%	83%	83%
55.5%	63%	70%	60%	55%	43%	42%
85.7%	94%	90%	83%	88%	72%	87%
83.2%	90%	86%	79%	85%	74%	85%
89.0%	90%	94%	90%	89%	81%	90%
79.0%	84%	84%	72%	87%	78%	69%
84.8%	86%	95%	82%	86%	79%	81%
62.0%	72%	72%	59%	63%	50%	56%
81.7%	90%	92%	65%	85%	79%	79%
85.0%	92%	88%	76%	89%	75%	90%
86.0%	90%	92%	70%	95%	76%	93%
58.5%	57%	60%	62%	44%	77%	51%
82.0%	86%	71%	91%	79%	82%	83%
85.5%	90%	92%	84%	86%	72%	89%
84.8%	90%	95%	93%	87%	61%	83%
91.5%	88%	91%	96%	91%	92%	91%
77.0%	88%	90%	60%	76%	80%	68%
73.5%	81%	75%	61%	79%	78%	67%
68.7%	77%	76%	73%	67%	56%	63%
64.7%	69%	57%	55%	70%	68%	69%
73.0%	69%	72%	65%	72%	72%	88%
83.8%	81%	93%	66%	90%	83%	90%
83.5%	84%	88%	84%	85%	70%	90%
50.7%	54%	56%	57%	42%	41%	54%
88.2%	85%	92%	93%	89%	85%	85%
83.0%	87%	91%	69%	88%	84%	79%
60.7%	59%	62%	61%	62%	65%	55%
87.0%	83%	85%	87%	93%	88%	86%
82.3%	74%	85%	78%	89%	91%	77%
75.0%	74%	81%	69%	75%	81%	70%
71.2%	79%	76%	58%	70%	79%	65%
82.0%	85%	90%	78%	82%	84%	73%
77.0%	88%	66%	84%	84%	71%	69%
82.5%	84%	79%	76%	85%	86%	85%
74.2%	75%	80%	68%	77%	70%	75%
51.8%	63%	60%	52%	52%	34%	50%
67.0%	74%	71%	46%	72%	76%	63%
86.7%	88%	90%	87%	82%	84%	89%
78.3%	84%	85%	76%	81%	65%	79%
86.2%	94%	92%	93%	90%	65%	83%
87.5%	89%	85%	93%	88%	83%	87%
80.0%	74%	79%	69%	82%	88%	88%
83.2%	88%	75%	85%	88%	77%	86%