	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 68.3%	4th 64.3%	5th 63.6%	1st 69.0%	6th 61.6%	3rd 66.9%
29.2%	32%	23%	28%	36%	18%	38%
62.5%	70%	71%	49%	54%	75%	56%
53.7%	60%	63%	61%	43%	44%	51%
72.2%	68%	78%	61%	74%	79%	73%
61.5%	65%	61%	70%	68%	46%	59%
77.8%	90%	54%	82%	76%	82%	83%
73.0%	72%	71%	79%	68%	77%	71%
56.8%	66%	45%	46%	69%	56%	59%
70.2%	76%	75%	68%	71%	67%	64%
89.0%	79%	81%	96%	96%	96%	86%
66.5%	75%	78%	63%	63%	57%	63%
66.7%	65%	56%	78%	72%	63%	66%
78.5%	89%	76%	72%	88%	64%	82%
70.2%	68%	73%	61%	67%	79%	73%
66.2%	68%	59%	53%	70%	74%	73%
34.7%	40%	29%	34%	38%	26%	41%
50.0%	48%	51%	45%	57%	41%	58%
69.8%	74%	66%	64%	73%	73%	69%
66.0%	67%	66%	63%	65%	70%	65%
72.3%	79%	70%	83%	83%	50%	69%
76.0%	82%	65%	80%	85%	68%	76%
54.3%	61%	38%	59%	53%	29%	86%
93.0%	99%	96%	98%	84%	97%	84%
70.2%	70%	63%	72%	72%	72%	72%
78.5%	89%	76%	72%	88%	64%	82%
61.8%	57%	63%	73%	68%	37%	73%
46.2%	50%	33%	43%	58%	48%	45%
80.7%	77%	78%	78%	87%	77%	87%
79.5%	97%	91%	10%	91%	96%	92%
64.8%	61%	67%	55%	68%	66%	72%
32.2%	32%	29%	38%	38%	18%	38%
60.0%	59%	56%	64%	59%	63%	59%
74.2%	67%	75%	78%	78%	78%	69%
74.8%	72%	77%	74%	79%	74%	73%
78.3%	82%	79%	79%	76%	69%	85%
67.3%	65%	63%	68%	75%	68%	65%
65.2%	66%	62%	65%	74%	59%	65%
42.0%	46%	36%	37%	42%	45%	46%
59.0%	61%	63%	65%	72%	38%	55%
88.8%	97%	82%	88%	96%	81%	89%
55.8%	63%	65%	56%	56%	41%	54%
54.0%	56%	55%	54%	54%	54%	51%
64.5%	68%	78%	51%	69%	66%	55%
69.8%	70%	71%	77%	79%	51%	71%
81.0%	81%	86%	80%	75%	82%	82%
59.8%	65%	64%	54%	67%	55%	54%