	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 78.2%	4th 75.4%	- -	1st 78.6%	5th 72.6%	3rd 76.6%
67.2%	66%	58%		76%	60%	76%
61.8%	62%	65%		51%	71%	60%
71.2%	92%	77%		69%	59%	59%
98.0%	98%	98%		98%	98%	98%
77.6%	72%	71%		64%	85%	96%
74.2%	66%	74%		65%	88%	78%
89.2%	91%	96%		88%	86%	85%
59.2%	62%	67%		55%	62%	50%
74.6%	76%	89%		89%	48%	71%
78.6%	74%	86%		82%	84%	67%
75.0%	82%	86%		75%	74%	58%
80.0%	83%	72%		92%	65%	88%
79.8%	81%	99%		90%	49%	80%
98.0%	98%	98%		98%	98%	98%
68.2%	79%	55%		69%	73%	65%
56.0%	61%	47%		61%	55%	56%
94.4%	92%	96%		98%	93%	93%
80.6%	79%	86%		80%	82%	76%
78.0%	78%	89%		80%	75%	68%
63.6%	78%	61%		71%	54%	54%
80.8%	78%	85%		80%	78%	83%
62.6%	65%	43%		60%	71%	74%
95.4%	91%	98%		91%	97%	100%
70.2%	75%	69%		66%	64%	77%
75.8%	77%	95%		86%	45%	76%
73.8%	75%	69%		87%	69%	69%
86.4%	87%	71%		88%	93%	93%
83.2%	89%	73%		90%	79%	85%
92.4%	89%	92%		96%	87%	98%
68.6%	71%	71%		63%	65%	73%
62.0%	69%	59%		75%	48%	59%
73.6%	80%	77%		74%	69%	68%
73.2%	70%	78%		80%	67%	71%
78.0%	89%	58%		87%	76%	80%
85.6%	86%	88%		90%	81%	83%
83.8%	76%	87%		77%	90%	89%
74.6%	77%	69%		75%	71%	81%
63.0%	77%	38%		75%	61%	64%
61.2%	63%	53%		70%	60%	60%
82.2%	90%	72%		89%	80%	80%
70.8%	71%	73%		70%	50%	90%
84.0%	82%	84%		86%	82%	86%
56.6%	53%	57%		51%	65%	57%
73.2%	67%	73%		81%	77%	68%
82.6%	93%	71%		87%	71%	91%
89.8%	89%	94%		90%	85%	91%