	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 68.6%	4th 64.7%	- -	1st 69.1%	5th 61.6%	3rd 67.9%
30.6%	32%	29%		36%	18%	38%
65.0%	69%	69%		54%	73%	60%
52.8%	61%	58%		50%	44%	51%
70.2%	68%	67%		74%	69%	73%
56.4%	65%	56%		61%	44%	56%
75.0%	90%	56%		76%	70%	83%
71.4%	72%	71%		68%	75%	71%
56.6%	65%	45%		56%	56%	61%
69.0%	77%	72%		62%	70%	64%
85.6%	79%	76%		96%	91%	86%
67.2%	69%	84%		63%	57%	63%
66.6%	65%	63%		72%	56%	77%
80.0%	91%	75%		88%	64%	82%
72.0%	68%	78%		67%	74%	73%
71.2%	68%	65%		75%	75%	73%
38.8%	33%	41%		47%	26%	47%
50.2%	48%	52%		57%	44%	50%
71.8%	74%	69%		73%	74%	69%
65.6%	67%	64%		70%	64%	63%
72.0%	78%	80%		83%	50%	69%
77.6%	82%	77%		81%	72%	76%
63.8%	70%	40%		70%	53%	86%
95.0%	99%	96%		84%	97%	99%
71.4%	71%	72%		72%	72%	70%
80.0%	91%	75%		88%	64%	82%
58.2%	57%	63%		68%	37%	66%
45.6%	50%	29%		58%	42%	49%
83.2%	89%	74%		89%	77%	87%
95.4%	97%	99%		91%	96%	94%
69.2%	62%	72%		66%	74%	72%
28.2%	32%	24%		29%	18%	38%
57.6%	59%	56%		59%	55%	59%
72.8%	67%	72%		78%	78%	69%
74.2%	72%	77%		78%	70%	74%
77.8%	82%	71%		79%	70%	87%
68.6%	65%	64%		75%	67%	72%
64.6%	66%	61%		66%	65%	65%
41.8%	43%	30%		44%	46%	46%
58.2%	61%	63%		72%	39%	56%
87.8%	97%	81%		91%	81%	89%
55.8%	63%	65%		56%	41%	54%
54.8%	56%	48%		59%	55%	56%
70.0%	68%	77%		76%	68%	61%
70.8%	70%	71%		79%	63%	71%
82.4%	81%	86%		79%	83%	83%
59.8%	65%	63%		62%	55%	54%