	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 68.3%	1st 69.0%	- -	3rd 66.7%	5th 58.3%	4th 63.1%
32.0%	32%	32%		34%	31%	31%
51.2%	56%	56%		42%	56%	46%
49.8%	68%	73%		41%	33%	34%
96.0%	96%	96%		96%	96%	96%
50.2%	36%	56%		49%	51%	59%
43.4%	30%	46%		42%	53%	46%
81.0%	88%	87%		80%	75%	75%
60.0%	61%	44%		66%	65%	64%
55.2%	51%	76%		66%	28%	55%
74.6%	83%	79%		72%	71%	68%
68.8%	83%	78%		63%	55%	65%
61.4%	61%	75%		67%	48%	56%
57.8%	69%	76%		65%	26%	53%
96.0%	96%	96%		96%	96%	96%
66.6%	66%	64%		66%	71%	66%
34.6%	35%	33%		36%	31%	38%
72.6%	71%	75%		72%	70%	75%
62.8%	67%	71%		58%	60%	58%
58.8%	63%	71%		47%	59%	54%
69.4%	83%	71%		83%	49%	61%
69.2%	69%	72%		69%	68%	68%
45.2%	62%	13%		41%	61%	49%
87.2%	82%	97%		80%	93%	84%
73.2%	73%	81%		68%	60%	84%
53.2%	65%	71%		60%	22%	48%
70.8%	74%	79%		81%	57%	63%
77.8%	89%	61%		86%	77%	76%
77.4%	86%	86%		76%	66%	73%
90.4%	88%	89%		88%	98%	89%
49.0%	56%	47%		38%	55%	49%
32.4%	35%	30%		42%	29%	26%
62.2%	70%	62%		67%	59%	53%
65.8%	76%	71%		65%	56%	61%
70.8%	82%	84%		78%	38%	72%
74.2%	71%	81%		86%	63%	70%
85.4%	86%	91%		95%	68%	87%
62.4%	72%	61%		63%	61%	55%
70.2%	75%	80%		78%	48%	70%
65.0%	76%	69%		72%	50%	58%
55.8%	54%	57%		61%	52%	55%
68.0%	67%	79%		81%	56%	57%
70.4%	72%	67%		72%	69%	72%
37.2%	38%	44%		32%	41%	31%
78.0%	74%	80%		83%	67%	86%
76.4%	81%	75%		82%	65%	79%
83.8%	74%	90%		85%	79%	91%