	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 63.3%	1st 64.4%	- -	3rd 62.3%	5th 59.1%	4th 60.4%
58.8%	59%	60%		59%	59%	57%
41.0%	34%	38%		38%	45%	50%
83.6%	86%	79%		85%	84%	84%
62.4%	61%	63%		63%	59%	66%
80.4%	81%	84%		81%	79%	77%
79.8%	81%	87%		82%	79%	70%
58.8%	58%	56%		64%	60%	56%
50.8%	51%	54%		47%	55%	47%
69.8%	68%	68%		68%	68%	77%
30.4%	32%	32%		25%	25%	38%
56.4%	66%	54%		64%	49%	49%
41.8%	44%	50%		43%	29%	43%
78.8%	82%	80%		80%	72%	80%
52.8%	53%	55%		50%	55%	51%
44.6%	48%	52%		42%	36%	45%
48.0%	55%	47%		47%	47%	44%
54.6%	63%	52%		55%	48%	55%
58.6%	64%	58%		63%	58%	50%
52.6%	51%	48%		59%	58%	47%
66.2%	64%	70%		63%	67%	67%
88.8%	83%	94%		94%	84%	89%
70.0%	74%	69%		70%	64%	73%
53.6%	56%	64%		57%	37%	54%
63.0%	70%	67%		70%	45%	63%
52.0%	47%	58%		55%	51%	49%
58.6%	60%	59%		59%	60%	55%
55.6%	53%	64%		46%	69%	46%
53.4%	57%	58%		53%	55%	44%
37.6%	40%	28%		49%	31%	40%
67.4%	62%	78%		71%	63%	63%
70.6%	77%	73%		68%	65%	70%
77.0%	75%	81%		75%	77%	77%
71.0%	73%	67%		73%	71%	71%
62.0%	65%	72%		55%	65%	53%
58.8%	66%	52%		54%	59%	63%
60.0%	61%	66%		55%	58%	60%
73.6%	79%	85%		72%	60%	72%
77.8%	81%	91%		80%	67%	70%
47.8%	47%	49%		43%	57%	43%
95.8%	94%	99%		94%	96%	96%
50.2%	53%	58%		53%	42%	45%
75.0%	72%	76%		78%	71%	78%
71.8%	77%	75%		75%	62%	70%