	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 68.1%	1st 68.3%	- -	3rd 66.5%	5th 58.7%	4th 63.0%
60.2%	71%	53%		56%	65%	56%
62.2%	65%	62%		59%	59%	66%
73.0%	73%	90%		80%	59%	63%
42.4%	46%	48%		40%	34%	44%
68.4%	67%	83%		67%	52%	73%
67.2%	69%	67%		67%	66%	67%
76.4%	79%	73%		82%	71%	77%
63.8%	75%	100%		51%	51%	42%
52.2%	58%	52%		57%	45%	49%
69.0%	75%	66%		72%	65%	67%
73.0%	73%	81%		72%	70%	69%
55.8%	53%	45%		60%	58%	63%
54.4%	61%	72%		59%	38%	42%
75.2%	83%	81%		73%	63%	76%
74.4%	82%	76%		75%	67%	72%
69.6%	75%	67%		73%	57%	76%
66.6%	69%	69%		69%	70%	56%
66.4%	70%	80%		71%	52%	59%
54.8%	58%	60%		60%	41%	55%
80.8%	89%	73%		85%	81%	76%
66.4%	78%	66%		70%	48%	70%
79.6%	72%	83%		87%	67%	89%
51.6%	62%	58%		41%	60%	37%
75.4%	86%	77%		75%	68%	71%
68.8%	72%	76%		68%	60%	68%
76.8%	89%	81%		90%	52%	72%
78.6%	83%	88%		76%	71%	75%
72.0%	78%	75%		74%	65%	68%
67.6%	70%	71%		68%	69%	60%
57.4%	52%	59%		67%	42%	67%
45.4%	45%	74%		38%	40%	30%
64.4%	65%	58%		62%	66%	71%
70.4%	75%	69%		71%	68%	69%
56.2%	61%	55%		53%	49%	63%
36.2%	43%	33%		42%	33%	30%
73.6%	75%	72%		69%	80%	72%
79.8%	83%	80%		80%	81%	75%
52.0%	53%	53%		58%	48%	48%
60.4%	51%	65%		70%	58%	58%
77.4%	81%	74%		78%	77%	77%
73.8%	76%	80%		71%	71%	71%
62.0%	63%	66%		57%	62%	62%
56.6%	57%	57%		58%	57%	54%
77.8%	82%	75%		77%	78%	77%
87.8%	85%	93%		83%	89%	89%
64.6%	64%	56%		80%	52%	71%
53.6%	67%	53%		67%	24%	57%
53.0%	55%	63%		49%	52%	46%
69.0%	71%	75%		65%	66%	68%
55.8%	56%	65%		64%	38%	56%
61.2%	68%	66%		69%	43%	60%
61.0%	59%	59%		69%	61%	57%
51.0%	45%	60%		48%	54%	48%
63.4%	64%	55%		69%	59%	70%