	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 68.3%	4th 64.8%	5th 63.8%	1st 68.8%	6th 63.0%	2nd 68.6%
29.8%	32%	27%	28%	36%	18%	38%
61.8%	66%	69%	51%	54%	75%	56%
54.8%	60%	63%	61%	50%	44%	51%
71.2%	68%	72%	61%	74%	79%	73%
59.2%	64%	54%	70%	65%	44%	58%
77.7%	87%	56%	82%	76%	82%	83%
73.7%	72%	71%	79%	68%	81%	71%
53.7%	65%	45%	51%	56%	52%	53%
69.7%	76%	72%	66%	67%	73%	64%
87.3%	79%	78%	96%	91%	96%	84%
66.5%	69%	84%	63%	63%	57%	63%
71.7%	63%	72%	78%	77%	59%	81%
81.5%	89%	75%	72%	96%	71%	86%
71.2%	68%	72%	61%	74%	79%	73%
67.7%	68%	67%	53%	70%	75%	73%
38.5%	41%	39%	34%	47%	29%	41%
49.2%	48%	48%	45%	57%	39%	58%
68.7%	74%	69%	65%	70%	70%	64%
66.8%	68%	67%	63%	70%	70%	63%
73.3%	79%	76%	83%	83%	50%	69%
76.3%	79%	75%	80%	81%	67%	76%
62.0%	72%	49%	59%	53%	53%	86%
96.0%	99%	99%	98%	84%	97%	99%
70.2%	73%	63%	69%	72%	72%	72%
81.5%	89%	75%	72%	96%	71%	86%
62.7%	57%	60%	81%	68%	37%	73%
42.3%	50%	29%	42%	42%	42%	49%
82.2%	78%	74%	78%	96%	77%	90%
80.7%	97%	96%	10%	91%	96%	94%
66.0%	61%	64%	55%	68%	74%	74%
31.3%	32%	24%	38%	38%	18%	38%
59.0%	60%	53%	64%	59%	58%	60%
73.7%	67%	72%	78%	78%	78%	69%
74.3%	72%	77%	74%	78%	71%	74%
78.8%	82%	80%	79%	76%	69%	87%
68.8%	65%	63%	68%	75%	67%	75%
65.5%	66%	66%	65%	66%	65%	65%
43.0%	45%	42%	38%	42%	45%	46%
58.5%	61%	57%	65%	66%	40%	62%
88.8%	97%	82%	88%	96%	81%	89%
56.5%	63%	65%	56%	56%	41%	58%
55.8%	56%	56%	54%	55%	58%	56%
64.5%	68%	66%	51%	69%	72%	61%
72.7%	70%	71%	77%	79%	68%	71%
81.0%	81%	85%	80%	75%	83%	82%
59.8%	65%	62%	54%	62%	55%	61%