	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 67.5%	2nd 68.3%	- -	1st 68.4%	5th 62.0%	3rd 67.7%
73.4%	74%	77%		79%	68%	69%
65.2%	59%	69%		68%	61%	69%
69.4%	82%	76%		71%	58%	60%
91.2%	88%	87%		100%	83%	98%
75.4%	81%	69%		100%	54%	73%
66.0%	56%	72%		68%	67%	67%
80.6%	85%	91%		75%	74%	78%
50.2%	48%	79%		36%	48%	40%
71.0%	71%	72%		75%	66%	71%
82.0%	73%	81%		84%	97%	75%
63.8%	75%	83%		60%	41%	60%
42.8%	38%	35%		48%	41%	52%
89.6%	97%	100%		81%	79%	91%
91.2%	88%	87%		100%	83%	98%
66.6%	67%	63%		65%	69%	69%
50.4%	56%	47%		49%	46%	54%
73.2%	77%	81%		73%	59%	76%
81.6%	80%	78%		82%	83%	85%
67.8%	65%	65%		68%	66%	75%
45.6%	51%	53%		52%	32%	40%
70.8%	72%	78%		70%	63%	71%
64.4%	80%	40%		67%	60%	75%
96.0%	96%	95%		92%	99%	98%
46.6%	46%	51%		46%	43%	47%
89.6%	97%	100%		81%	79%	91%
50.0%	50%	53%		54%	39%	54%
34.4%	37%	17%		39%	40%	39%
64.6%	62%	59%		75%	56%	71%
90.4%	87%	90%		85%	94%	96%
56.0%	53%	58%		52%	57%	60%
69.0%	70%	69%		76%	54%	76%
70.4%	70%	68%		69%	69%	76%
74.6%	68%	78%		79%	79%	69%
60.6%	59%	62%		60%	59%	63%
47.4%	46%	46%		49%	49%	47%
68.2%	69%	71%		61%	71%	69%
50.2%	47%	51%		54%	48%	51%
43.2%	41%	49%		44%	38%	44%
48.8%	51%	51%		66%	29%	47%
78.4%	74%	78%		78%	78%	84%
60.8%	67%	69%		62%	44%	62%
65.6%	64%	68%		60%	72%	64%
82.2%	83%	85%		85%	79%	79%
61.0%	59%	61%		69%	55%	61%
63.6%	67%	64%		73%	52%	62%
68.8%	81%	66%		67%	73%	57%