	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 63.5%	1st 67.6%	6th 57.5%	3rd 64.5%	5th 58.0%	2nd 65.1%
29.7%	25%	29%	31%	28%	19%	46%
48.2%	49%	52%	31%	48%	64%	45%
43.5%	52%	54%	38%	42%	33%	42%
68.0%	68%	67%	57%	72%	72%	72%
69.8%	69%	82%	51%	65%	81%	71%
54.7%	47%	71%	51%	53%	53%	53%
79.3%	73%	95%	80%	76%	77%	75%
51.8%	46%	33%	50%	54%	59%	69%
55.3%	53%	71%	52%	60%	46%	50%
72.5%	83%	76%	69%	72%	69%	66%
66.5%	65%	86%	70%	64%	50%	64%
58.0%	55%	59%	69%	60%	45%	60%
51.3%	69%	73%	33%	64%	26%	43%
69.7%	69%	70%	57%	74%	74%	74%
62.2%	69%	54%	53%	61%	69%	67%
27.8%	26%	39%	21%	22%	28%	31%
77.8%	83%	84%	70%	79%	72%	79%
61.7%	65%	66%	47%	61%	66%	65%
59.3%	62%	69%	45%	62%	56%	62%
69.0%	75%	79%	79%	73%	41%	67%
73.8%	70%	75%	63%	82%	73%	80%
40.0%	39%	32%	26%	39%	43%	61%
84.2%	82%	88%	79%	77%	88%	91%
69.7%	66%	86%	62%	69%	67%	68%
46.8%	65%	68%	28%	59%	22%	39%
66.7%	60%	74%	79%	73%	41%	73%
81.0%	80%	72%	88%	84%	78%	84%
78.2%	77%	76%	86%	80%	65%	85%
76.5%	88%	89%	10%	88%	98%	86%
41.5%	33%	49%	23%	42%	59%	43%
31.7%	31%	28%	34%	28%	26%	43%
64.8%	63%	66%	67%	63%	67%	63%
67.0%	69%	78%	66%	65%	60%	64%
76.3%	69%	87%	83%	78%	69%	72%
73.0%	72%	79%	76%	71%	63%	77%
79.3%	80%	87%	54%	86%	82%	87%
61.8%	66%	64%	63%	49%	61%	68%
66.2%	71%	74%	58%	71%	58%	65%
58.0%	60%	51%	73%	69%	38%	57%
62.8%	71%	69%	56%	69%	52%	60%
72.3%	74%	74%	88%	73%	52%	73%
67.5%	65%	67%	73%	64%	60%	76%
37.3%	43%	39%	18%	44%	40%	40%
77.7%	76%	78%	73%	86%	67%	86%
71.5%	70%	66%	81%	81%	58%	73%
82.2%	77%	86%	85%	85%	81%	79%