	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 75.5%	2nd 73.1%	6th 67.0%	3rd 71.4%	5th 68.4%	4th 70.9%
59.3%	69%	53%	70%	53%	60%	51%
77.5%	84%	66%	84%	74%	71%	86%
90.8%	95%	84%	99%	89%	87%	91%
64.0%	69%	64%	60%	59%	67%	65%
62.5%	66%	52%	55%	59%	65%	78%
76.0%	76%	80%	69%	82%	69%	80%
72.5%	74%	79%	63%	75%	72%	72%
59.7%	77%	100%	44%	37%	59%	41%
70.2%	71%	72%	59%	78%	69%	72%
66.8%	72%	73%	60%	68%	64%	64%
78.5%	79%	83%	83%	80%	74%	72%
60.0%	62%	49%	63%	62%	62%	62%
47.2%	61%	72%	10%	59%	37%	44%
75.7%	83%	77%	71%	74%	75%	74%
67.3%	69%	72%	72%	64%	64%	63%
86.3%	87%	81%	84%	96%	82%	88%
77.0%	86%	81%	71%	80%	69%	75%
79.2%	80%	80%	80%	82%	77%	76%
58.3%	72%	57%	54%	63%	43%	61%
71.2%	78%	75%	59%	72%	71%	72%
68.3%	72%	73%	63%	70%	62%	70%
72.0%	78%	80%	65%	74%	63%	72%
50.7%	56%	56%	51%	33%	73%	35%
61.0%	61%	47%	71%	60%	66%	61%
79.3%	76%	85%	83%	76%	71%	85%
74.8%	82%	81%	81%	76%	57%	72%
82.8%	84%	76%	85%	84%	84%	84%
63.7%	70%	71%	48%	69%	62%	62%
72.8%	80%	75%	64%	72%	78%	68%
56.7%	62%	55%	57%	57%	52%	57%
73.3%	81%	78%	52%	72%	85%	72%
62.3%	63%	49%	62%	62%	65%	73%
77.3%	84%	84%	62%	80%	75%	79%
74.3%	71%	74%	85%	74%	65%	77%
65.5%	73%	69%	68%	62%	53%	68%
70.5%	63%	76%	66%	72%	71%	75%
83.2%	86%	92%	73%	83%	83%	82%
64.0%	73%	65%	59%	63%	61%	63%
80.2%	74%	81%	80%	88%	80%	78%
73.3%	73%	77%	70%	75%	77%	68%
73.7%	71%	85%	67%	71%	77%	71%
75.8%	88%	81%	58%	66%	88%	74%
75.3%	79%	75%	74%	77%	73%	74%
85.2%	89%	78%	88%	91%	74%	91%
84.0%	86%	81%	80%	83%	87%	87%
66.3%	74%	69%	60%	73%	61%	61%
55.0%	78%	58%	47%	59%	28%	60%
58.8%	64%	61%	46%	59%	63%	60%
83.3%	90%	93%	73%	78%	88%	78%
70.3%	77%	77%	67%	81%	51%	69%
74.8%	83%	75%	83%	75%	58%	75%
76.7%	83%	68%	75%	80%	77%	77%
83.3%	78%	89%	77%	80%	87%	89%
67.3%	67%	61%	67%	75%	61%	73%