	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%	1st 68.4%	4th 65.0%	3rd 67.4%	6th 60.6%	5th 63.2%
58.0%	72%	42%	74%	60%	56%	44%
66.3%	66%	62%	65%	68%	71%	66%
71.8%	74%	90%	74%	78%	53%	62%
43.2%	47%	50%	46%	35%	42%	39%
57.8%	48%	88%	52%	62%	52%	45%
62.0%	61%	66%	73%	73%	53%	46%
73.7%	71%	62%	72%	81%	77%	79%
56.3%	69%	100%	55%	25%	51%	38%
53.3%	55%	52%	55%	57%	45%	56%
69.2%	73%	62%	69%	72%	64%	75%
76.0%	74%	73%	73%	75%	89%	72%
62.8%	59%	60%	68%	67%	61%	62%
52.3%	61%	75%	55%	59%	22%	42%
77.5%	81%	78%	81%	80%	63%	82%
74.2%	80%	72%	73%	73%	71%	76%
76.8%	86%	66%	80%	82%	67%	80%
68.2%	71%	74%	62%	71%	64%	67%
63.8%	72%	73%	58%	73%	51%	56%
64.0%	52%	65%	70%	63%	65%	69%
80.7%	88%	70%	70%	87%	81%	88%
68.7%	68%	60%	91%	75%	48%	70%
74.8%	67%	78%	89%	71%	67%	77%
56.5%	67%	71%	51%	53%	54%	43%
72.3%	80%	67%	64%	80%	71%	72%
68.7%	69%	68%	71%	74%	58%	72%
74.8%	83%	67%	89%	87%	52%	71%
79.3%	76%	93%	73%	77%	78%	79%
69.7%	78%	80%	54%	74%	69%	63%
65.0%	71%	71%	50%	69%	68%	61%
76.8%	83%	74%	78%	80%	73%	73%
20.8%	16%	59%	7%	19%	16%	8%
67.5%	72%	66%	73%	69%	54%	71%
70.0%	81%	73%	62%	71%	64%	69%
59.2%	61%	42%	78%	59%	49%	66%
44.8%	52%	51%	44%	42%	42%	38%
76.0%	72%	81%	80%	75%	71%	77%
73.3%	79%	74%	59%	83%	70%	75%
76.2%	75%	83%	74%	75%	75%	75%
58.2%	57%	57%	52%	67%	58%	58%
76.7%	76%	80%	81%	77%	70%	76%
73.5%	76%	79%	63%	80%	78%	65%
58.8%	62%	64%	53%	56%	62%	56%
59.2%	62%	64%	59%	62%	54%	54%
76.5%	82%	72%	76%	77%	76%	76%
86.0%	85%	89%	80%	83%	89%	90%
68.8%	72%	72%	68%	72%	73%	56%
71.0%	91%	73%	63%	70%	68%	61%
45.8%	50%	61%	28%	46%	44%	46%
68.7%	67%	70%	66%	73%	65%	71%
51.8%	44%	61%	57%	52%	40%	57%
62.8%	71%	62%	73%	67%	43%	61%
60.0%	55%	61%	57%	67%	58%	62%
57.5%	53%	60%	63%	52%	60%	57%
58.8%	73%	31%	61%	65%	59%	64%