	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 73.1%	2nd 72.4%	- -	3rd 71.0%	5th 65.9%	4th 67.9%
55.8%	67%	48%		55%	62%	47%
60.8%	67%	56%		56%	52%	73%
79.2%	85%	87%		76%	74%	74%
64.4%	69%	79%		56%	57%	61%
72.2%	79%	64%		76%	65%	77%
72.0%	65%	71%		76%	78%	70%
64.8%	71%	65%		65%	64%	59%
65.6%	77%	100%		41%	72%	38%
68.6%	72%	79%		68%	61%	63%
71.6%	74%	76%		70%	73%	65%
78.2%	78%	83%		76%	75%	79%
85.8%	88%	82%		92%	86%	81%
54.6%	61%	72%		61%	41%	38%
70.0%	77%	82%		70%	50%	71%
68.2%	71%	69%		72%	60%	69%
73.2%	83%	65%		73%	64%	81%
57.0%	56%	65%		57%	62%	45%
80.6%	75%	86%		81%	79%	82%
63.0%	71%	62%		69%	51%	62%
83.4%	87%	84%		83%	86%	77%
74.8%	79%	74%		79%	64%	78%
84.4%	93%	87%		83%	86%	73%
53.2%	54%	58%		35%	76%	43%
76.0%	79%	77%		71%	76%	77%
70.6%	75%	80%		72%	52%	74%
76.0%	83%	80%		81%	58%	78%
94.0%	95%	96%		95%	90%	94%
84.4%	83%	83%		90%	85%	81%
64.0%	69%	70%		72%	53%	56%
52.0%	53%	53%		51%	44%	59%
50.4%	49%	61%		50%	51%	41%
64.2%	60%	53%		69%	65%	74%
69.6%	72%	69%		71%	69%	67%
68.4%	67%	71%		72%	66%	66%
43.2%	50%	46%		35%	39%	46%
81.8%	86%	71%		84%	77%	91%
85.8%	88%	84%		88%	87%	82%
48.4%	51%	42%		62%	41%	46%
75.4%	73%	76%		75%	74%	79%
85.6%	85%	83%		90%	89%	81%
85.4%	91%	89%		87%	82%	78%
61.4%	66%	66%		56%	65%	54%
65.6%	62%	81%		76%	53%	56%
67.0%	78%	70%		72%	51%	64%
92.0%	92%	88%		97%	93%	90%
53.2%	49%	52%		63%	45%	57%
39.6%	51%	41%		51%	11%	44%
66.8%	73%	66%		67%	65%	63%
82.0%	83%	89%		83%	86%	69%
75.0%	79%	83%		78%	60%	75%
76.8%	85%	77%		80%	60%	82%
80.4%	74%	78%		79%	90%	81%
86.2%	86%	84%		86%	88%	87%
59.6%	59%	54%		60%	56%	69%