	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 82.7%	2nd 82.0%	6th 74.2%	3rd 79.3%	4th 75.4%	5th 74.7%
55.3%	60%	50%	63%	60%	54%	45%
82.0%	92%	93%	79%	84%	71%	73%
81.3%	84%	86%	94%	86%	69%	69%
72.5%	76%	74%	70%	70%	71%	74%
72.0%	85%	76%	75%	60%	73%	63%
80.0%	90%	88%	87%	79%	84%	52%
87.7%	95%	93%	74%	91%	83%	90%
59.3%	67%	96%	56%	41%	51%	45%
66.2%	66%	79%	60%	70%	59%	63%
75.0%	80%	80%	58%	79%	79%	74%
86.5%	91%	85%	68%	94%	89%	92%
90.0%	91%	93%	95%	84%	93%	84%
51.5%	65%	70%	44%	57%	44%	29%
87.5%	89%	83%	88%	89%	86%	90%
85.8%	88%	83%	87%	89%	85%	83%
85.5%	94%	92%	85%	93%	71%	78%
77.3%	80%	83%	69%	81%	77%	74%
81.3%	86%	95%	70%	87%	76%	74%
84.3%	91%	88%	84%	80%	83%	80%
72.7%	78%	76%	67%	73%	80%	62%
85.0%	84%	92%	78%	88%	83%	85%
89.0%	98%	90%	79%	91%	92%	84%
55.8%	69%	58%	51%	37%	72%	48%
82.2%	88%	90%	77%	84%	77%	77%
84.0%	83%	91%	86%	86%	76%	82%
87.8%	95%	92%	88%	93%	69%	90%
91.7%	91%	88%	93%	93%	92%	93%
73.0%	82%	87%	57%	78%	77%	57%
77.7%	87%	82%	56%	91%	77%	73%
86.7%	89%	89%	88%	76%	89%	89%
53.8%	50%	74%	44%	56%	41%	58%
84.2%	88%	71%	85%	91%	82%	88%
76.8%	84%	80%	57%	79%	81%	80%
81.0%	82%	79%	82%	84%	76%	83%
65.8%	68%	80%	62%	64%	61%	60%
85.2%	94%	93%	82%	83%	80%	79%
78.8%	85%	81%	72%	78%	81%	76%
75.2%	78%	80%	67%	78%	78%	70%
84.2%	80%	77%	82%	91%	86%	89%
87.8%	85%	89%	86%	87%	91%	89%
83.2%	85%	88%	79%	89%	79%	79%
74.3%	82%	81%	69%	71%	73%	70%
71.7%	83%	76%	66%	75%	53%	77%
83.7%	83%	83%	90%	85%	81%	80%
79.7%	87%	80%	76%	72%	77%	86%
84.8%	78%	89%	82%	88%	89%	83%
60.3%	81%	67%	56%	59%	47%	52%
63.5%	73%	68%	51%	60%	70%	59%
78.5%	84%	79%	79%	81%	72%	76%
78.0%	66%	83%	85%	81%	76%	77%
88.0%	92%	88%	89%	93%	76%	90%
88.7%	89%	83%	88%	92%	89%	91%
90.5%	88%	92%	90%	96%	86%	91%
70.5%	85%	45%	64%	84%	66%	79%