	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 71.1%	3rd 67.1%	6th 63.4%	2nd 68.0%	5th 65.0%	4th 65.4%
45.5%	51%	30%	53%	51%	50%	38%
77.7%	83%	84%	73%	81%	55%	90%
57.3%	60%	60%	62%	56%	46%	60%
57.0%	60%	58%	54%	45%	56%	69%
60.7%	69%	44%	60%	64%	64%	63%
68.8%	81%	54%	75%	75%	74%	54%
70.0%	70%	53%	74%	84%	74%	65%
62.8%	63%	100%	56%	44%	70%	44%
55.3%	53%	72%	43%	53%	53%	58%
56.3%	59%	62%	53%	55%	56%	53%
86.0%	85%	91%	78%	91%	85%	86%
62.0%	63%	56%	66%	67%	60%	60%
63.7%	76%	89%	53%	76%	30%	58%
81.3%	74%	76%	82%	90%	79%	87%
59.3%	60%	62%	59%	62%	54%	59%
64.2%	67%	71%	66%	70%	49%	62%
44.0%	47%	47%	38%	49%	44%	39%
61.5%	68%	54%	65%	76%	53%	53%
79.0%	77%	92%	75%	72%	92%	66%
64.7%	77%	78%	58%	64%	58%	53%
59.7%	66%	62%	50%	62%	56%	62%
66.5%	70%	69%	62%	66%	70%	62%
49.5%	58%	61%	51%	36%	46%	45%
58.5%	62%	38%	65%	62%	62%	62%
80.0%	89%	75%	76%	78%	86%	76%
85.2%	82%	82%	92%	79%	76%	100%
93.2%	100%	92%	74%	100%	100%	93%
55.8%	62%	64%	42%	62%	58%	47%
63.3%	69%	76%	35%	76%	67%	57%
93.0%	93%	93%	93%	93%	93%	93%
28.5%	28%	70%	15%	16%	25%	17%
63.8%	75%	57%	60%	66%	74%	51%
72.5%	81%	63%	72%	71%	70%	78%
51.7%	56%	41%	48%	56%	51%	58%
60.8%	67%	79%	58%	62%	55%	44%
67.8%	83%	61%	68%	65%	61%	69%
71.2%	70%	66%	65%	83%	64%	79%
79.5%	79%	79%	71%	92%	77%	79%
78.2%	100%	64%	69%	76%	80%	80%
75.2%	72%	72%	78%	74%	72%	83%
59.2%	60%	50%	58%	63%	61%	63%
55.5%	67%	62%	50%	53%	52%	49%
65.2%	70%	57%	61%	71%	71%	61%
75.0%	77%	67%	74%	77%	78%	77%
72.0%	75%	75%	76%	62%	75%	69%
87.8%	77%	93%	85%	79%	93%	100%
69.5%	78%	77%	63%	55%	77%	67%
53.3%	65%	65%	41%	48%	54%	47%
65.7%	70%	70%	62%	70%	62%	60%
61.2%	67%	63%	61%	66%	60%	50%
78.3%	81%	79%	78%	85%	59%	88%
76.7%	76%	69%	82%	74%	81%	78%
83.5%	92%	64%	82%	85%	85%	93%
67.0%	77%	37%	66%	85%	59%	78%