	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 66.7%	5th 59.5%	- -	2nd 63.9%	4th 60.9%	3rd 62.6%
56.2%	60%	43%		59%	60%	59%
35.6%	30%	0%		58%	43%	47%
83.0%	85%	75%		84%	79%	92%
57.4%	66%	55%		55%	55%	56%
79.8%	78%	95%		78%	71%	77%
81.4%	74%	86%		74%	87%	86%
50.0%	44%	58%		49%	55%	44%
57.6%	65%	59%		58%	59%	47%
62.8%	65%	64%		67%	62%	56%
60.0%	80%	55%		55%	55%	55%
41.2%	60%	20%		41%	47%	38%
76.2%	75%	80%		71%	80%	75%
75.2%	76%	76%		86%	53%	85%
64.0%	54%	72%		65%	59%	70%
46.0%	46%	50%		50%	29%	55%
55.4%	55%	75%		51%	47%	49%
59.8%	77%	58%		64%	45%	55%
60.4%	58%	67%		58%	61%	58%
47.8%	53%	48%		53%	32%	53%
56.4%	66%	64%		56%	49%	47%
71.8%	79%	31%		79%	76%	94%
60.8%	75%	24%		75%	63%	67%
49.2%	45%	43%		50%	51%	57%
64.8%	72%	65%		74%	51%	62%
55.2%	61%	56%		51%	64%	44%
59.6%	61%	63%		57%	60%	57%
60.6%	72%	74%		38%	69%	50%
53.2%	67%	31%		63%	58%	47%
59.0%	71%	67%		56%	64%	37%
69.4%	77%	56%		68%	67%	79%
72.0%	79%	69%		74%	65%	73%
75.6%	75%	86%		68%	81%	68%
72.0%	70%	63%		80%	67%	80%
50.0%	53%	36%		54%	49%	58%
60.2%	69%	40%		54%	69%	69%
59.0%	62%	41%		67%	62%	63%
71.0%	70%	77%		83%	53%	72%
74.0%	69%	92%		70%	59%	80%
54.2%	60%	57%		54%	57%	43%
93.2%	98%	95%		87%	99%	87%
52.8%	51%	67%		53%	43%	50%
84.2%	86%	75%		83%	90%	87%
68.2%	78%	50%		77%	73%	63%