	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 66.7%	4th 66.7%	6th 60.5%	1st 67.3%	5th 62.5%	2nd 67.1%
73.4%	74%	77%		79%	68%	69%
63.5%	59%	69%	59%	62%	68%	64%
67.2%	73%	76%		71%	58%	58%
90.8%	88%	85%		100%	83%	98%
71.4%	81%	75%		74%	54%	73%
64.0%	56%	60%		70%	67%	67%
82.2%	85%	97%		77%	74%	78%
50.4%	48%	79%		36%	54%	35%
68.8%	72%	64%		71%	66%	71%
78.4%	73%	81%		84%	83%	71%
66.4%	75%	85%		64%	44%	64%
42.8%	38%	35%		48%	41%	52%
88.0%	97%	93%		81%	79%	90%
90.8%	88%	85%		100%	83%	98%
64.6%	65%	63%		65%	65%	65%
49.4%	51%	53%		41%	44%	58%
70.6%	74%	69%		73%	61%	76%
81.8%	80%	77%		82%	83%	87%
69.0%	65%	68%		73%	67%	72%
46.6%	51%	53%		53%	36%	40%
68.8%	72%	78%	62%	71%	63%	67%
64.4%	71%	41%		67%	59%	84%
95.8%	96%	94%		92%	99%	98%
41.4%	38%	37%		40%	43%	49%
88.0%	97%	93%		81%	79%	90%
47.2%	50%	46%		47%	39%	54%
31.6%	37%	0%		39%	43%	39%
63.2%	56%	58%		75%	56%	71%
91.2%	87%	90%		85%	98%	96%
56.6%	53%	52%		60%	60%	58%
69.0%	70%	65%		76%	57%	77%
69.6%	70%	71%		68%	69%	70%
72.0%	64%	68%		76%	79%	73%
61.0%	64%	59%		60%	59%	63%
46.8%	46%	47%		42%	49%	50%
66.2%	69%	69%		61%	71%	61%
50.0%	47%	50%		54%	48%	51%
42.2%	44%	49%		44%	38%	36%
48.0%	51%	51%		62%	29%	47%
77.4%	74%	73%		78%	78%	84%
61.8%	67%	69%		62%	49%	62%
66.8%	66%	74%		60%	70%	64%
82.2%	79%	80%		91%	83%	78%
60.2%	59%	61%		64%	56%	61%
64.0%	67%	72%		69%	52%	60%
71.0%	81%	77%		67%	73%	57%