	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 70.9%	5th 64.2%	4th 66.3%	1st 71.7%	6th 61.9%	3rd 70.0%
63.8%	65%	67%	62%	67%	55%	67%
64.3%	61%	34%	70%	76%	74%	71%
71.5%	72%	57%	72%	67%	84%	77%
71.8%	83%	74%	71%	64%	64%	75%
81.2%	79%	87%	64%	81%	87%	89%
87.3%	86%	75%	89%	83%	92%	99%
71.8%	75%	54%	70%	75%	76%	81%
78.3%	85%	73%	59%	85%	84%	84%
79.2%	74%	92%	78%	76%	76%	79%
68.3%	66%	64%	77%	63%	63%	77%
69.8%	77%	72%	80%	62%	70%	58%
72.7%	77%	65%	72%	69%	79%	74%
75.5%	83%	74%	71%	90%	56%	79%
42.8%	59%	30%	51%	43%	27%	47%
71.7%	75%	72%	88%	82%	49%	64%
70.5%	75%	60%	66%	79%	61%	82%
72.7%	83%	94%	55%	83%	54%	67%
50.7%	56%	71%	20%	49%	61%	47%
36.2%	30%	63%	28%	33%	41%	22%
69.8%	56%	77%	69%	71%	73%	73%
68.3%	70%	54%	83%	80%	45%	78%
63.7%	67%	53%	74%	74%	43%	71%
53.8%	50%	54%	57%	53%	56%	53%
67.2%	73%	82%	56%	64%	44%	84%
49.3%	57%	32%	58%	57%	45%	47%
58.3%	64%	41%	70%	68%	34%	73%
57.5%	63%	54%	48%	65%	58%	57%
72.0%	81%	62%	59%	82%	74%	74%
73.0%	80%	80%	70%	74%	63%	71%
62.2%	69%	77%	37%	65%	61%	64%
60.0%	55%	65%	74%	72%	39%	55%
56.3%	53%	72%	56%	61%	45%	51%
69.2%	75%	57%	72%	67%	67%	77%
75.8%	79%	65%	76%	79%	82%	74%
63.3%	72%	31%	73%	60%	72%	72%
64.3%	64%	47%	76%	66%	65%	68%
67.3%	66%	70%	72%	83%	49%	64%
84.3%	96%	86%	83%	94%	67%	80%
61.3%	64%	55%	75%	65%	46%	63%
93.8%	91%	89%	94%	100%	100%	89%
72.0%	77%	58%	64%	82%	70%	81%
59.5%	66%	56%	39%	74%	51%	71%
80.7%	100%	66%	74%	100%	61%	83%