	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 68.6%	1st 70.7%	6th 57.8%	3rd 68.1%	5th 62.6%	4th 65.4%
72.3%	83%	77%	41%	77%	79%	77%
83.0%	82%	71%	87%	84%	88%	86%
78.8%	75%	75%	87%	84%	77%	75%
35.2%	36%	38%	33%	39%	23%	42%
83.2%	82%	84%	87%	82%	80%	84%
68.8%	76%	81%	52%	66%	69%	69%
64.8%	58%	80%	62%	71%	60%	58%
64.3%	73%	85%	36%	65%	61%	66%
85.8%	92%	89%	68%	88%	89%	89%
41.0%	39%	56%	43%	46%	14%	48%
84.8%	84%	89%	87%	82%	78%	89%
29.3%	30%	36%	25%	40%	9%	36%
75.5%	86%	80%	59%	74%	78%	76%
88.8%	90%	90%	86%	92%	91%	84%
68.7%	65%	69%	54%	61%	93%	70%
55.3%	62%	67%	34%	53%	60%	56%
52.0%	61%	61%	38%	60%	46%	46%
57.0%	70%	65%	36%	64%	61%	46%
63.5%	72%	49%	61%	72%	60%	67%
62.5%	55%	75%	62%	70%	58%	55%
76.0%	86%	78%	56%	83%	81%	72%
72.7%	77%	83%	53%	77%	68%	78%
72.2%	77%	77%	78%	72%	45%	84%
71.0%	79%	72%	59%	77%	68%	71%
60.5%	61%	62%	57%	63%	60%	60%
67.7%	64%	65%	69%	72%	60%	76%
56.0%	62%	69%	37%	51%	62%	55%
46.5%	54%	71%	33%	38%	49%	34%
32.8%	38%	39%	25%	42%	7%	46%
58.0%	56%	61%	58%	66%	54%	53%
70.5%	80%	78%	58%	64%	72%	71%
74.3%	79%	81%	67%	73%	67%	79%
56.7%	53%	59%	63%	61%	51%	53%
70.5%	77%	79%	68%	78%	62%	59%
54.2%	64%	32%	65%	60%	32%	72%
70.7%	77%	87%	54%	79%	69%	58%
70.3%	65%	71%	72%	72%	72%	70%
87.3%	85%	84%	84%	89%	94%	88%
51.3%	58%	61%	34%	49%	61%	45%
92.5%	89%	89%	99%	98%	91%	89%
69.8%	70%	100%	53%	63%	79%	54%
53.0%	51%	56%	43%	50%	62%	56%
68.7%	77%	71%	63%	82%	50%	69%