	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 73.7%	1st 75.1%	- -	3rd 73.0%	4th 71.4%	5th 71.0%
63.2%	78%	59%		63%	63%	53%
88.8%	90%	89%		93%	81%	91%
90.6%	94%	94%		97%	77%	91%
74.0%	81%	74%		72%	70%	73%
67.8%	77%	49%		61%	69%	83%
61.4%	51%	61%		67%	73%	55%
71.6%	71%	71%		75%	74%	67%
61.2%	75%	100%		37%	55%	39%
75.6%	71%	70%		84%	75%	78%
68.0%	66%	68%		66%	71%	69%
75.6%	65%	80%		71%	83%	79%
82.4%	82%	74%		86%	82%	88%
54.2%	61%	75%		53%	41%	41%
80.8%	87%	81%		84%	70%	82%
86.8%	91%	89%		89%	76%	89%
85.0%	85%	88%		88%	79%	85%
68.8%	71%	74%		69%	68%	62%
83.0%	87%	92%		83%	74%	79%
53.0%	58%	56%		54%	48%	49%
80.2%	79%	80%		85%	83%	74%
85.2%	82%	89%		88%	82%	85%
82.8%	82%	83%		84%	89%	76%
47.4%	52%	47%		41%	60%	37%
81.6%	88%	79%		81%	79%	81%
81.4%	85%	84%		81%	74%	83%
86.8%	90%	90%		90%	72%	92%
89.0%	85%	92%		85%	89%	94%
78.0%	84%	84%		76%	78%	68%
74.2%	75%	81%		76%	74%	65%
60.2%	67%	60%		61%	53%	60%
63.0%	65%	63%		63%	61%	63%
54.2%	43%	44%		60%	56%	68%
67.8%	59%	67%		69%	74%	70%
80.8%	82%	85%		85%	75%	77%
42.8%	38%	43%		42%	42%	49%
80.0%	65%	92%		79%	85%	79%
67.0%	71%	67%		66%	72%	59%
52.4%	49%	47%		44%	68%	54%
80.4%	72%	85%		87%	78%	80%
76.0%	66%	88%		73%	86%	67%
75.6%	68%	87%		72%	83%	68%
64.8%	69%	66%		59%	75%	55%
68.2%	65%	80%		67%	67%	62%
76.8%	77%	75%		87%	70%	75%
73.2%	72%	73%		76%	75%	70%
67.6%	73%	67%		70%	59%	69%
51.8%	63%	61%		49%	37%	49%
58.0%	64%	55%		58%	63%	50%
83.2%	97%	96%		75%	75%	73%
72.0%	75%	79%		72%	62%	72%
80.2%	82%	84%		85%	68%	82%
87.4%	87%	85%		87%	89%	89%
91.2%	83%	97%		87%	93%	96%
80.2%	85%	55%		91%	81%	89%