	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 70.6%	4th 68.3%	5th 68.0%	1st 70.9%	6th 62.2%	3rd 70.3%
77.5%	80%	81%	72%	76%	77%	79%
54.7%	58%	42%	50%	63%	52%	63%
79.5%	76%	74%	86%	79%	82%	80%
63.0%	70%	65%	65%	62%	34%	82%
76.5%	86%	84%	78%	69%	71%	71%
76.7%	71%	75%	84%	76%	72%	82%
66.3%	60%	76%	65%	65%	65%	67%
74.0%	74%	82%	57%	77%	77%	77%
66.7%	65%	65%	58%	72%	68%	72%
58.5%	62%	71%	56%	66%	30%	66%
77.5%	83%	68%	83%	83%	65%	83%
47.3%	52%	51%	43%	51%	36%	51%
65.7%	70%	68%	76%	68%	44%	68%
59.5%	62%	60%	60%	60%	52%	63%
78.7%	87%	76%	83%	77%	67%	82%
66.2%	67%	65%	68%	65%	63%	69%
71.3%	75%	86%	74%	63%	59%	71%
47.8%	52%	60%	35%	62%	44%	34%
40.5%	44%	51%	32%	41%	51%	24%
64.8%	60%	53%	63%	71%	71%	71%
76.0%	77%	70%	87%	77%	66%	79%
76.2%	84%	72%	91%	72%	60%	78%
81.7%	85%	90%	89%	92%	58%	76%
57.2%	67%	58%	63%	61%	39%	55%
64.8%	67%	67%	62%	62%	62%	69%
53.8%	53%	53%	49%	60%	50%	58%
71.8%	74%	82%	61%	70%	71%	73%
81.8%	78%	70%	79%	90%	85%	89%
52.5%	71%	50%	49%	64%	14%	67%
61.7%	59%	76%	55%	60%	56%	64%
64.7%	67%	58%	76%	68%	55%	64%
50.8%	50%	56%	44%	50%	55%	50%
79.5%	80%	74%	86%	79%	78%	80%
77.2%	82%	69%	75%	83%	75%	79%
64.2%	76%	52%	68%	79%	52%	58%
71.7%	72%	56%	77%	73%	78%	74%
88.8%	85%	88%	87%	89%	89%	95%
58.5%	58%	67%	62%	69%	44%	51%
88.5%	92%	90%	79%	91%	89%	90%
87.8%	88%	82%	95%	88%	86%	88%
73.7%	77%	63%	74%	77%	74%	77%
73.8%	72%	74%	59%	80%	76%	82%
70.0%	67%	65%	68%	67%	81%	72%