	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 70.0%	3rd 67.4%	6th 63.4%	1st 70.2%	5th 64.7%	4th 67.1%
43.3%	44%	47%	32%	48%	36%	53%
57.7%	62%	63%	48%	56%	62%	55%
43.2%	59%	46%	37%	40%	46%	31%
100.0%	100%	100%	100%	100%	100%	100%
72.7%	68%	73%	69%	73%	72%	81%
78.3%	58%	100%	78%	70%	83%	81%
72.5%	79%	70%	73%	74%	74%	65%
40.0%	48%	75%	22%	26%	37%	32%
64.8%	64%	73%	65%	82%	56%	49%
79.3%	82%	73%	72%	85%	80%	84%
56.7%	64%	63%	57%	59%	49%	48%
77.3%	83%	72%	83%	79%	64%	83%
75.2%	75%	100%	84%	84%	34%	74%
100.0%	100%	100%	100%	100%	100%	100%
57.2%	65%	52%	40%	61%	68%	57%
41.0%	42%	37%	41%	51%	37%	38%
50.2%	50%	41%	57%	56%	56%	41%
72.5%	80%	72%	58%	79%	72%	74%
79.2%	82%	83%	70%	82%	76%	82%
56.5%	67%	54%	54%	63%	50%	51%
50.8%	45%	48%	58%	57%	38%	59%
60.0%	64%	22%	70%	64%	76%	64%
84.7%	81%	83%	87%	83%	91%	83%
65.8%	61%	64%	60%	70%	70%	70%
75.2%	75%	100%	84%	84%	34%	74%
73.8%	73%	75%	76%	76%	68%	75%
74.2%	81%	73%	71%	73%	73%	74%
78.8%	75%	80%	78%	72%	84%	84%
81.7%	98%	100%	10%	100%	87%	95%
60.8%	68%	53%	53%	60%	79%	52%
39.0%	49%	19%	41%	49%	37%	39%
64.2%	65%	56%	72%	68%	69%	55%
86.3%	93%	100%	78%	86%	80%	81%
62.5%	65%	75%	67%	56%	56%	56%
75.7%	80%	76%	76%	80%	71%	71%
86.5%	90%	79%	69%	87%	94%	100%
44.5%	44%	33%	43%	49%	51%	47%
48.2%	54%	22%	49%	51%	57%	56%
59.5%	63%	55%	59%	75%	42%	63%
75.5%	85%	61%	66%	86%	82%	73%
66.3%	71%	68%	74%	70%	54%	61%
71.0%	76%	70%	67%	69%	71%	73%
77.3%	81%	81%	58%	79%	89%	76%
66.2%	60%	67%	65%	70%	58%	77%
61.3%	62%	59%	62%	59%	62%	64%
81.3%	91%	87%	84%	87%	52%	87%