	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 63.8%	4th 63.6%	- -	1st 64.0%	5th 58.2%	3rd 63.7%
48.2%	50%	45%		56%	41%	49%
60.6%	65%	60%		55%	65%	58%
44.6%	52%	54%		42%	33%	42%
74.2%	75%	74%		76%	70%	76%
50.0%	52%	54%		45%	48%	51%
79.6%	83%	63%		84%	84%	84%
65.0%	69%	60%		63%	65%	68%
55.2%	64%	30%		68%	47%	67%
74.2%	71%	87%		71%	71%	71%
78.4%	65%	77%		82%	90%	78%
56.6%	55%	76%		55%	42%	55%
46.6%	43%	45%		53%	36%	56%
66.2%	73%	75%		83%	42%	58%
73.8%	73%	72%		78%	68%	78%
49.6%	55%	40%		53%	47%	53%
28.8%	32%	28%		28%	28%	28%
86.4%	84%	89%		90%	79%	90%
66.4%	68%	66%		66%	66%	66%
60.2%	59%	68%		58%	58%	58%
48.8%	56%	57%		55%	27%	49%
63.4%	62%	64%		64%	60%	67%
58.6%	68%	36%		55%	55%	79%
84.0%	80%	87%		83%	87%	83%
42.8%	32%	56%		44%	39%	43%
66.2%	73%	75%		83%	42%	58%
57.6%	56%	62%		58%	39%	73%
66.2%	65%	49%		70%	73%	74%
69.6%	72%	59%		76%	65%	76%
87.2%	80%	91%		83%	91%	91%
64.2%	54%	65%		57%	72%	73%
66.4%	68%	59%		68%	68%	69%
58.6%	59%	57%		59%	59%	59%
68.6%	66%	65%		73%	76%	63%
63.2%	61%	68%		60%	60%	67%
75.6%	79%	86%		68%	60%	85%
89.0%	90%	88%		84%	94%	89%
70.2%	72%	71%		63%	71%	74%
49.0%	51%	73%		47%	33%	41%
43.6%	51%	38%		59%	23%	47%
71.0%	63%	76%		65%	78%	73%
54.0%	61%	61%		56%	39%	53%
55.4%	67%	68%		51%	60%	31%
55.4%	57%	55%		55%	55%	55%
63.8%	63%	65%		73%	53%	65%
70.2%	72%	74%		69%	67%	69%
54.6%	67%	59%		59%	51%	37%