	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 82.2%	1st 82.3%	5th 76.7%	3rd 81.8%	6th 76.2%	4th 78.1%
65.7%	76%	61%	79%	62%	67%	49%
84.7%	84%	92%	81%	87%	75%	89%
85.7%	92%	88%	94%	89%	67%	84%
76.0%	77%	81%	71%	74%	73%	80%
70.0%	88%	50%	85%	58%	55%	84%
85.0%	89%	85%	88%	86%	90%	72%
88.0%	94%	94%	77%	92%	83%	88%
59.0%	67%	96%	53%	38%	55%	45%
72.0%	74%	69%	69%	80%	67%	73%
82.0%	88%	82%	72%	89%	84%	77%
81.5%	80%	79%	69%	93%	77%	91%
85.8%	74%	86%	92%	86%	89%	88%
60.5%	66%	84%	61%	58%	49%	45%
89.0%	92%	91%	89%	89%	79%	94%
87.2%	92%	82%	87%	89%	85%	88%
86.0%	81%	90%	82%	93%	80%	90%
74.2%	76%	78%	64%	78%	77%	72%
81.3%	87%	94%	73%	90%	66%	78%
83.5%	88%	85%	78%	82%	80%	88%
86.3%	87%	95%	78%	91%	87%	80%
87.8%	87%	85%	89%	93%	76%	97%
89.7%	86%	92%	84%	96%	86%	94%
56.0%	66%	68%	57%	46%	52%	47%
81.7%	88%	86%	80%	81%	79%	76%
83.7%	81%	86%	89%	86%	74%	86%
87.3%	93%	86%	93%	95%	67%	90%
93.5%	98%	91%	89%	97%	92%	94%
76.2%	85%	91%	58%	85%	71%	67%
77.7%	87%	86%	51%	92%	79%	71%
85.2%	91%	79%	92%	83%	89%	77%
59.7%	49%	73%	47%	66%	62%	61%
78.0%	70%	70%	66%	88%	88%	86%
83.2%	88%	85%	63%	90%	92%	81%
77.8%	79%	83%	73%	77%	80%	75%
56.5%	60%	55%	63%	52%	64%	45%
88.5%	79%	92%	91%	92%	90%	87%
80.5%	82%	80%	76%	82%	84%	79%
80.5%	80%	75%	80%	82%	87%	79%
84.8%	74%	85%	81%	93%	86%	90%
78.2%	76%	82%	77%	85%	70%	79%
81.8%	86%	89%	75%	80%	83%	78%
77.2%	84%	82%	61%	76%	85%	75%
75.8%	81%	74%	74%	79%	70%	77%
83.0%	92%	79%	89%	88%	72%	78%
84.2%	89%	86%	80%	81%	81%	88%
85.3%	80%	96%	83%	88%	90%	75%
66.5%	86%	65%	65%	65%	59%	59%
64.5%	72%	68%	54%	63%	71%	59%
88.0%	90%	96%	90%	86%	77%	89%
73.5%	68%	85%	77%	77%	54%	80%
88.7%	95%	93%	95%	95%	71%	83%
88.0%	80%	90%	91%	93%	89%	85%
93.8%	94%	100%	94%	92%	89%	94%
76.0%	89%	48%	74%	91%	72%	82%