	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 63.1%	1st 68.7%	- -	2nd 65.4%	5th 57.7%	3rd 64.8%
29.8%	25%	31%		28%	19%	46%
52.8%	49%	60%		48%	56%	51%
47.2%	52%	55%		50%	37%	42%
71.4%	68%	78%		67%	72%	72%
71.8%	70%	78%		59%	81%	71%
54.6%	47%	67%		53%	53%	53%
79.4%	73%	95%		76%	78%	75%
53.2%	46%	40%		57%	54%	69%
56.0%	50%	74%		60%	46%	50%
73.0%	78%	76%		72%	73%	66%
67.0%	65%	89%		67%	50%	64%
55.2%	49%	59%		56%	45%	67%
55.4%	69%	73%		69%	26%	40%
71.2%	69%	70%		69%	74%	74%
62.6%	65%	54%		62%	66%	66%
26.8%	26%	19%		30%	28%	31%
81.4%	83%	80%		79%	86%	79%
62.6%	62%	66%		65%	61%	59%
62.8%	62%	79%		62%	56%	55%
67.0%	75%	81%		73%	41%	65%
75.4%	70%	76%		82%	68%	81%
42.4%	39%	30%		39%	43%	61%
86.2%	82%	88%		77%	93%	91%
69.8%	65%	74%		75%	67%	68%
50.8%	65%	68%		63%	22%	36%
64.2%	61%	81%		62%	44%	73%
80.6%	80%	78%		84%	78%	83%
75.8%	77%	72%		80%	65%	85%
92.8%	88%	94%		91%	94%	97%
45.4%	33%	49%		43%	59%	43%
28.4%	31%	36%		28%	18%	29%
62.8%	63%	66%		64%	58%	63%
64.6%	69%	69%		65%	56%	64%
75.0%	67%	89%		78%	69%	72%
70.4%	72%	82%		75%	46%	77%
85.0%	83%	83%		87%	87%	85%
65.2%	65%	64%		64%	61%	72%
69.6%	71%	83%		71%	58%	65%
57.0%	60%	61%		69%	38%	57%
64.6%	71%	69%		70%	52%	61%
72.4%	74%	78%		73%	64%	73%
67.8%	65%	67%		71%	60%	76%
41.8%	43%	43%		44%	44%	35%
80.8%	80%	85%		86%	67%	86%
69.6%	70%	66%		81%	58%	73%
81.8%	77%	87%		85%	81%	79%