	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 64.4%	1st 65.8%	5th 62.7%	2nd 65.2%	6th 57.5%	4th 64.3%
66.2%	66%	69%	66%	70%	53%	73%
58.7%	64%	61%	52%	54%	61%	60%
53.3%	61%	61%	61%	47%	45%	45%
60.5%	62%	63%	54%	60%	59%	65%
76.8%	81%	79%	65%	89%	67%	80%
68.0%	58%	90%	58%	72%	69%	61%
79.2%	79%	90%	78%	75%	75%	78%
47.8%	49%	61%	32%	55%	52%	38%
71.5%	71%	71%	73%	77%	68%	69%
60.3%	57%	59%	69%	63%	61%	53%
65.2%	71%	78%	61%	66%	58%	57%
62.2%	58%	62%	77%	58%	51%	67%
72.3%	76%	76%	82%	69%	60%	71%
60.5%	62%	59%	54%	60%	63%	65%
44.5%	37%	39%	47%	52%	46%	46%
46.7%	48%	48%	52%	48%	36%	48%
66.8%	69%	73%	62%	65%	65%	67%
53.5%	57%	65%	44%	52%	51%	52%
60.8%	59%	56%	58%	66%	61%	65%
65.8%	75%	73%	75%	68%	41%	63%
51.2%	43%	50%	57%	55%	44%	58%
68.5%	80%	63%	69%	76%	40%	83%
74.7%	78%	80%	69%	69%	75%	77%
71.2%	78%	56%	71%	76%	69%	77%
72.2%	78%	78%	78%	74%	56%	69%
49.7%	50%	58%	62%	48%	31%	49%
54.8%	54%	43%	57%	55%	59%	61%
68.2%	63%	68%	76%	73%	57%	72%
86.7%	84%	86%	76%	84%	90%	100%
69.3%	78%	82%	52%	74%	65%	65%
47.2%	49%	50%	61%	47%	17%	59%
60.8%	63%	56%	66%	60%	59%	61%
62.5%	60%	70%	65%	65%	56%	59%
55.0%	54%	73%	51%	54%	44%	54%
50.3%	51%	52%	47%	53%	46%	53%
82.7%	79%	81%	79%	82%	86%	89%
61.0%	66%	62%	56%	60%	62%	60%
52.2%	57%	60%	43%	61%	45%	47%
42.0%	44%	36%	53%	54%	24%	41%
69.3%	74%	61%	75%	75%	61%	70%
65.2%	67%	67%	58%	67%	67%	65%
60.5%	58%	59%	54%	60%	64%	68%
67.0%	76%	72%	53%	70%	73%	58%
85.7%	90%	89%	82%	84%	80%	89%
55.2%	53%	54%	65%	57%	44%	58%
88.8%	77%	88%	88%	100%	88%	92%