	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 69.8%	4th 65.6%	- -	1st 70.8%	5th 64.7%	3rd 66.9%
43.6%	44%	47%		50%	36%	41%
57.4%	62%	52%		56%	62%	55%
46.6%	59%	46%		45%	46%	37%
100.0%	100%	100%		100%	100%	100%
74.4%	68%	78%		73%	72%	81%
78.0%	58%	82%		76%	93%	81%
69.6%	79%	70%		70%	64%	65%
41.6%	44%	61%		34%	37%	32%
63.2%	64%	66%		80%	56%	50%
81.2%	78%	77%		87%	80%	84%
58.2%	64%	72%		59%	48%	48%
76.2%	83%	72%		79%	64%	83%
70.2%	75%	76%		84%	42%	74%
100.0%	100%	100%		100%	100%	100%
55.0%	65%	41%		61%	58%	50%
41.8%	42%	43%		49%	37%	38%
50.6%	50%	50%		56%	56%	41%
74.4%	80%	72%		74%	72%	74%
79.8%	82%	81%		80%	74%	82%
57.0%	67%	54%		63%	50%	51%
49.2%	45%	49%		57%	38%	57%
59.2%	64%	22%		64%	76%	70%
81.4%	81%	87%		73%	83%	83%
60.8%	61%	33%		74%	66%	70%
70.2%	75%	76%		84%	42%	74%
74.8%	73%	75%		81%	70%	75%
74.2%	74%	73%		73%	77%	74%
80.4%	78%	80%		80%	80%	84%
99.6%	98%	100%		100%	100%	100%
65.4%	68%	53%		74%	79%	53%
42.4%	47%	37%		52%	37%	39%
62.0%	65%	53%		68%	69%	55%
85.8%	93%	89%		86%	80%	81%
61.6%	65%	75%		56%	56%	56%
75.0%	80%	76%		76%	71%	72%
91.0%	90%	85%		90%	90%	100%
44.8%	44%	33%		49%	51%	47%
51.0%	54%	41%		51%	53%	56%
59.2%	63%	55%		75%	40%	63%
76.2%	85%	61%		80%	82%	73%
63.6%	71%	60%		70%	54%	63%
72.8%	78%	70%		73%	70%	73%
81.8%	81%	81%		79%	89%	79%
64.2%	63%	67%		70%	58%	63%
60.8%	62%	59%		57%	62%	64%
82.0%	91%	87%		87%	58%	87%