	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 81.1%	2nd 80.9%	6th 71.8%	3rd 77.8%	5th 73.0%	4th 74.9%
57.5%	60%	56%	62%	57%	60%	50%
79.2%	85%	74%	74%	80%	72%	90%
74.5%	86%	84%	67%	76%	69%	65%
74.3%	76%	77%	77%	79%	68%	69%
80.3%	84%	70%	78%	71%	84%	95%
80.0%	79%	84%	78%	78%	75%	86%
90.3%	96%	92%	80%	88%	94%	92%
57.2%	77%	92%	42%	38%	49%	45%
61.7%	61%	62%	53%	73%	65%	56%
76.8%	82%	82%	71%	74%	78%	74%
91.8%	88%	98%	91%	92%	92%	90%
89.2%	91%	93%	89%	90%	82%	90%
46.0%	65%	63%	10%	54%	44%	40%
84.8%	87%	85%	76%	90%	81%	90%
84.0%	90%	84%	77%	90%	80%	83%
84.2%	90%	92%	73%	85%	73%	92%
78.7%	80%	87%	68%	81%	81%	75%
72.3%	76%	86%	62%	76%	73%	61%
70.7%	82%	88%	68%	73%	47%	66%
66.2%	69%	72%	51%	66%	77%	62%
83.0%	83%	86%	72%	88%	81%	88%
84.2%	97%	90%	69%	86%	83%	80%
50.0%	51%	49%	53%	45%	55%	47%
79.0%	88%	81%	71%	79%	76%	79%
82.5%	83%	87%	78%	84%	80%	83%
83.7%	94%	93%	81%	85%	66%	83%
92.2%	95%	91%	90%	95%	93%	89%
72.2%	81%	84%	60%	71%	77%	60%
80.8%	87%	83%	74%	86%	81%	74%
66.2%	69%	78%	69%	67%	51%	63%
62.8%	64%	59%	47%	77%	73%	57%
85.8%	82%	90%	86%	86%	80%	91%
78.3%	82%	85%	72%	76%	80%	75%
81.8%	83%	83%	82%	83%	75%	85%
57.5%	64%	60%	58%	57%	53%	53%
84.5%	85%	87%	82%	88%	81%	84%
80.7%	85%	83%	75%	81%	77%	83%
65.3%	70%	77%	68%	69%	55%	53%
89.2%	88%	84%	91%	92%	89%	91%
88.2%	81%	93%	91%	92%	94%	78%
88.5%	89%	75%	90%	95%	93%	89%
71.7%	75%	83%	59%	71%	78%	64%
75.3%	79%	89%	66%	80%	59%	79%
84.8%	95%	93%	93%	94%	63%	71%
81.0%	85%	80%	81%	74%	82%	84%
72.5%	70%	81%	76%	67%	64%	77%
60.0%	76%	80%	60%	57%	30%	57%
66.2%	73%	68%	54%	72%	67%	63%
74.2%	82%	76%	61%	70%	80%	76%
81.3%	88%	79%	82%	87%	73%	79%
84.7%	91%	89%	89%	83%	72%	84%
86.2%	84%	81%	91%	89%	86%	86%
85.5%	88%	82%	82%	84%	86%	91%
76.0%	88%	66%	76%	81%	67%	78%