	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 67.1%	1st 68.0%	- -	3rd 65.2%	5th 61.7%	4th 63.9%
26.6%	23%	34%		22%	24%	30%
67.2%	66%	76%		67%	68%	59%
86.6%	84%	86%		89%	83%	91%
74.8%	83%	70%		74%	74%	73%
54.6%	57%	72%		55%	38%	51%
78.2%	89%	75%		87%	62%	78%
52.6%	52%	59%		50%	51%	51%
50.6%	55%	59%		54%	34%	51%
60.8%	63%	61%		50%	82%	48%
83.6%	83%	85%		81%	76%	93%
59.6%	56%	65%		61%	57%	59%
56.0%	71%	46%		49%	66%	48%
60.6%	71%	59%		55%	55%	63%
64.6%	72%	61%		70%	50%	70%
31.2%	31%	41%		25%	34%	25%
93.2%	95%	97%		96%	82%	96%
68.8%	67%	69%		68%	71%	69%
54.0%	59%	49%		58%	55%	49%
61.8%	58%	69%		69%	55%	58%
51.8%	65%	45%		65%	25%	59%
77.8%	81%	77%		72%	81%	78%
63.0%	64%	65%		66%	60%	60%
87.6%	88%	92%		82%	81%	95%
63.2%	60%	62%		66%	64%	64%
33.0%	31%	30%		29%	39%	36%
74.6%	79%	63%		65%	83%	83%
63.6%	70%	67%		56%	59%	66%
61.4%	52%	66%		63%	63%	63%
47.4%	51%	55%		48%	37%	46%
74.4%	79%	87%		71%	92%	43%
62.0%	60%	64%		65%	56%	65%
57.0%	61%	54%		61%	53%	56%
75.4%	69%	82%		80%	73%	73%
71.6%	74%	71%		80%	62%	71%
57.8%	60%	60%		59%	56%	54%
75.4%	75%	77%		70%	84%	71%
77.4%	76%	70%		80%	81%	80%
58.6%	54%	62%		54%	62%	61%
69.2%	77%	77%		68%	62%	62%
58.6%	62%	55%		63%	62%	51%
62.2%	70%	53%		63%	64%	61%
67.2%	79%	63%		71%	48%	75%
74.4%	77%	80%		81%	56%	78%
69.0%	70%	70%		67%	72%	66%
61.8%	74%	62%		74%	39%	60%
50.4%	44%	67%		47%	47%	47%
53.4%	52%	57%		54%	50%	54%
75.0%	71%	78%		78%	74%	74%
54.4%	62%	54%		54%	44%	58%
74.6%	83%	80%		71%	63%	76%
71.0%	69%	66%		76%	75%	69%
78.0%	75%	83%		84%	79%	69%
55.8%	59%	51%		59%	48%	62%
47.2%	54%	57%		44%	42%	39%
64.8%	66%	68%		55%	69%	66%
61.4%	63%	84%		58%	51%	51%
34.4%	46%	37%		42%	22%	25%
70.6%	63%	81%		77%	68%	64%
72.4%	80%	68%		77%	58%	79%
84.8%	84%	89%		71%	97%	83%
63.8%	66%	71%		59%	61%	62%
67.4%	69%	70%		68%	70%	60%
56.0%	47%	59%		52%	67%	55%
64.0%	61%	71%		57%	66%	65%
73.4%	68%	73%		77%	73%	76%
78.8%	75%	83%		83%	81%	72%
55.2%	57%	64%		46%	59%	50%
74.2%	73%	77%		70%	83%	68%
62.6%	67%	59%		59%	60%	68%
62.2%	69%	37%		81%	52%	72%
70.4%	83%	65%		88%	48%	68%
49.6%	48%	54%		53%	40%	53%
53.0%	55%	60%		45%	64%	41%
64.0%	56%	68%		62%	75%	59%
72.0%	72%	78%		68%	60%	82%
81.6%	73%	79%		83%	86%	87%
88.4%	89%	94%		75%	97%	87%
60.6%	53%	64%		53%	65%	68%
69.6%	83%	70%		72%	52%	71%
52.6%	61%	75%		59%	22%	46%
59.8%	75%	81%		53%	48%	42%
75.4%	76%	81%		71%	74%	75%
59.2%	51%	65%		63%	61%	56%
71.8%	79%	77%		69%	62%	72%
76.6%	75%	73%		78%	82%	75%
74.0%	82%	81%		71%	62%	74%
78.6%	86%	81%		74%	71%	81%
67.6%	58%	74%		72%	66%	68%
67.0%	72%	76%		72%	54%	61%
88.6%	93%	89%		87%	88%	86%
63.8%	70%	75%		67%	51%	56%