	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 70.0%	2nd 68.3%	- -	3rd 68.2%	5th 63.9%	4th 66.2%
61.2%	73%	56%		60%	65%	52%
56.0%	60%	54%		57%	47%	62%
70.4%	71%	87%		78%	56%	60%
58.2%	58%	71%		57%	48%	57%
72.6%	81%	60%		73%	78%	71%
69.0%	70%	70%		70%	67%	68%
72.0%	74%	74%		70%	71%	71%
47.4%	75%	8%		38%	72%	44%
68.2%	68%	71%		63%	72%	67%
68.6%	74%	70%		67%	62%	70%
66.8%	68%	73%		69%	60%	64%
63.0%	56%	60%		71%	64%	64%
56.0%	61%	80%		57%	41%	41%
68.6%	71%	70%		73%	62%	67%
80.0%	83%	79%		82%	77%	79%
71.8%	73%	72%		71%	69%	74%
68.4%	67%	71%		69%	74%	61%
74.2%	68%	88%		73%	70%	72%
51.0%	50%	50%		56%	43%	56%
68.8%	71%	74%		69%	65%	65%
60.6%	68%	63%		64%	47%	61%
73.8%	81%	78%		72%	64%	74%
42.8%	43%	43%		31%	65%	32%
68.6%	76%	60%		73%	67%	67%
73.4%	78%	71%		75%	71%	72%
60.0%	72%	61%		70%	38%	59%
83.6%	83%	94%		81%	79%	81%
74.0%	75%	82%		75%	73%	65%
79.0%	81%	82%		81%	81%	70%
60.8%	58%	64%		65%	52%	65%
71.8%	71%	80%		69%	81%	58%
55.0%	54%	54%		57%	52%	58%
74.2%	84%	76%		76%	66%	69%
64.0%	63%	62%		70%	52%	73%
33.4%	43%	33%		31%	29%	31%
79.0%	79%	75%		79%	79%	83%
70.8%	72%	65%		72%	68%	77%
54.2%	54%	53%		54%	54%	56%
74.4%	78%	66%		81%	74%	73%
81.2%	75%	88%		72%	87%	84%
65.6%	65%	65%		61%	72%	65%
79.4%	83%	86%		76%	80%	72%
81.0%	85%	87%		71%	81%	81%
77.0%	81%	85%		78%	63%	78%
85.4%	88%	89%		75%	87%	88%
57.6%	59%	60%		64%	38%	67%
40.0%	50%	33%		48%	18%	51%
71.2%	74%	71%		73%	71%	67%
81.0%	76%	82%		78%	85%	84%
79.2%	82%	84%		85%	68%	77%
57.2%	61%	61%		72%	37%	55%
75.6%	81%	68%		89%	73%	67%
75.0%	67%	79%		73%	78%	78%
63.4%	69%	49%		70%	58%	71%