	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	3rd 68.2%	2nd 68.3%	6th 62.2%	1st 69.0%	5th 63.7%	4th 67.8%
43.3%	44%	44%	36%	48%	47%	41%
59.8%	65%	63%	51%	62%	65%	53%
43.3%	46%	50%	41%	40%	41%	42%
69.8%	68%	69%	62%	72%	74%	74%
72.5%	78%	78%	73%	77%	60%	69%
84.7%	77%	87%	93%	81%	89%	81%
71.7%	73%	72%	66%	69%	74%	76%
45.2%	48%	58%	29%	40%	54%	42%
73.3%	68%	75%	71%	82%	76%	68%
78.5%	78%	80%	72%	82%	85%	74%
60.3%	62%	72%	61%	59%	47%	61%
73.0%	72%	68%	79%	75%	67%	77%
70.8%	79%	84%	64%	84%	42%	72%
69.8%	68%	69%	62%	72%	74%	74%
54.7%	55%	51%	38%	62%	70%	52%
40.7%	43%	42%	33%	45%	36%	45%
62.7%	60%	65%	58%	68%	61%	64%
69.2%	76%	68%	65%	66%	74%	66%
75.0%	80%	70%	73%	75%	73%	79%
50.3%	51%	58%	58%	58%	29%	48%
53.3%	50%	48%	61%	57%	40%	64%
62.2%	70%	44%	69%	51%	64%	75%
84.2%	80%	91%	91%	73%	87%	83%
68.3%	74%	68%	62%	70%	66%	70%
70.8%	79%	84%	64%	84%	42%	72%
68.2%	61%	75%	78%	70%	54%	71%
66.2%	72%	59%	66%	71%	56%	73%
84.5%	84%	86%	83%	88%	83%	83%
80.2%	98%	91%	10%	100%	91%	91%
76.3%	72%	90%	62%	76%	84%	74%
43.3%	44%	45%	42%	41%	42%	46%
65.7%	67%	62%	60%	67%	69%	69%
86.8%	89%	98%	78%	85%	86%	85%
55.2%	53%	66%	58%	56%	56%	42%
73.3%	77%	69%	74%	77%	74%	69%
85.5%	81%	78%	74%	90%	90%	100%
50.3%	49%	51%	54%	43%	51%	54%
51.3%	54%	45%	50%	54%	49%	56%
55.8%	53%	66%	59%	67%	31%	59%
82.8%	82%	80%	83%	90%	82%	80%
67.3%	72%	61%	74%	68%	55%	74%
70.8%	76%	63%	60%	73%	78%	75%
84.8%	91%	93%	68%	89%	89%	79%
67.0%	69%	67%	64%	74%	54%	74%
63.2%	65%	64%	64%	65%	58%	63%
74.5%	86%	77%	66%	78%	62%	78%