	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 66.5%	4th 62.2%	6th 61.1%	1st 66.6%	5th 61.3%	3rd 64.9%
60.2%	62%	63%	55%	63%	63%	55%
57.7%	64%	71%	38%	54%	65%	54%
36.0%	54%	24%	37%	42%	21%	38%
91.0%	91%	91%	91%	91%	91%	91%
45.5%	45%	55%	37%	39%	43%	54%
80.7%	67%	86%	82%	81%	84%	84%
63.8%	58%	68%	64%	61%	66%	66%
60.2%	70%	30%	68%	60%	68%	65%
61.3%	65%	66%	60%	77%	52%	48%
72.0%	61%	63%	69%	79%	82%	78%
59.8%	69%	64%	61%	61%	61%	43%
51.7%	58%	39%	56%	61%	40%	56%
72.5%	79%	62%	83%	83%	54%	74%
91.0%	91%	91%	91%	91%	91%	91%
50.0%	62%	40%	41%	53%	57%	47%
45.7%	50%	48%	40%	48%	48%	40%
66.0%	64%	58%	71%	72%	58%	73%
66.3%	65%	70%	65%	66%	66%	66%
59.5%	61%	66%	56%	58%	58%	58%
47.0%	61%	44%	43%	64%	27%	43%
64.0%	65%	66%	59%	64%	63%	67%
66.0%	83%	30%	66%	70%	63%	84%
88.5%	87%	91%	96%	83%	91%	83%
41.7%	32%	56%	41%	39%	39%	43%
72.5%	79%	62%	83%	83%	54%	74%
63.5%	64%	62%	77%	77%	39%	62%
64.8%	73%	32%	61%	73%	80%	70%
71.3%	80%	62%	78%	73%	62%	73%
76.3%	87%	91%	10%	83%	96%	91%
46.8%	57%	38%	34%	50%	51%	51%
75.2%	76%	80%	73%	82%	63%	77%
60.0%	63%	57%	63%	63%	59%	55%
63.2%	65%	61%	60%	75%	56%	62%
62.5%	57%	73%	58%	60%	60%	67%
80.5%	77%	86%	82%	76%	77%	85%
89.0%	90%	90%	86%	83%	90%	95%
72.3%	76%	60%	76%	77%	68%	77%
45.3%	51%	59%	33%	47%	41%	41%
49.5%	57%	39%	39%	66%	48%	48%
82.7%	69%	91%	83%	73%	90%	90%
61.3%	65%	66%	59%	59%	58%	61%
54.5%	47%	58%	56%	56%	59%	51%
52.2%	55%	55%	39%	54%	55%	55%
64.7%	70%	65%	59%	74%	55%	65%
70.3%	70%	71%	74%	61%	72%	74%
56.5%	67%	59%	58%	59%	37%	59%