	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 72.4%	5th 67.6%	6th 66.0%	1st 72.9%	4th 68.2%	3rd 68.5%
65.4%	67%	55%		77%	59%	69%
81.8%	90%	83%		77%	86%	73%
48.8%	64%	48%		48%	39%	45%
100.0%	100%	100%		100%	100%	100%
53.0%	59%	55%		63%	40%	48%
64.2%	54%	72%		61%	72%	62%
72.6%	71%	71%		75%	75%	71%
52.6%	55%	56%		49%	54%	49%
69.6%	83%	59%		88%	49%	69%
61.4%	60%	62%		70%	59%	56%
57.6%	71%	75%		60%	41%	41%
63.2%	56%	68%		89%	45%	58%
84.8%	91%	74%		83%	86%	90%
100.0%	100%	100%		100%	100%	100%
69.8%	73%	66%		67%	74%	69%
61.6%	59%	57%		75%	58%	59%
84.0%	85%	78%		79%	92%	86%
80.4%	78%	76%		85%	86%	77%
73.5%	77%	81%	66%	74%	69%	74%
50.0%	73%	46%		60%	30%	41%
72.0%	76%	65%		74%	62%	83%
69.2%	80%	38%		75%	78%	75%
94.2%	98%	96%		93%	92%	92%
65.8%	72%	53%		63%	67%	74%
84.0%	89%	73%		82%	87%	89%
75.0%	83%	71%		88%	67%	66%
57.8%	71%	31%		62%	61%	64%
78.8%	80%	79%		78%	78%	79%
94.0%	98%	96%		92%	92%	92%
49.6%	48%	48%		43%	60%	49%
55.8%	65%	15%		74%	65%	60%
81.8%	83%	88%		88%	79%	71%
60.2%	56%	74%		61%	56%	54%
77.0%	85%	83%		82%	71%	64%
65.6%	66%	66%		66%	64%	66%
81.6%	71%	88%		83%	88%	78%
58.2%	56%	60%		61%	63%	51%
53.6%	55%	41%		56%	57%	59%
49.4%	50%	49%		61%	42%	45%
69.2%	68%	67%		73%	66%	72%
64.0%	60%	63%		64%	74%	59%
73.0%	72%	78%		75%	70%	70%
54.0%	56%	58%		52%	50%	54%
64.2%	59%	60%		71%	64%	67%
82.6%	77%	92%		71%	88%	85%
89.0%	89%	95%		84%	82%	95%