	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 75.3%	1st 75.4%	6th 59.7%	3rd 71.7%	5th 68.7%	4th 70.6%
49.7%	53%	53%	55%	54%	39%	44%
84.2%	83%	77%	89%	87%	77%	92%
84.5%	92%	88%	94%	83%	79%	71%
69.2%	72%	70%	68%	72%	64%	69%
63.8%	70%	66%	46%	65%	59%	77%
74.3%	72%	78%	55%	81%	82%	78%
77.2%	86%	87%	53%	80%	81%	76%
42.0%	67%	6%	38%	46%	57%	38%
70.3%	75%	83%	55%	70%	66%	73%
65.3%	73%	85%	38%	63%	72%	61%
87.5%	89%	99%	64%	89%	91%	93%
77.2%	75%	63%	75%	84%	80%	86%
50.0%	65%	77%	10%	58%	45%	45%
80.0%	86%	89%	63%	82%	78%	82%
74.8%	84%	86%	56%	73%	81%	69%
85.5%	85%	79%	94%	87%	80%	88%
69.8%	73%	79%	57%	77%	70%	63%
70.5%	70%	86%	68%	64%	64%	71%
54.3%	62%	82%	38%	56%	32%	56%
64.0%	76%	77%	44%	60%	71%	56%
78.5%	84%	88%	57%	76%	88%	78%
74.5%	90%	79%	49%	77%	84%	68%
52.2%	58%	48%	58%	45%	58%	46%
74.5%	82%	71%	67%	80%	72%	75%
78.5%	85%	87%	60%	78%	80%	81%
81.2%	88%	85%	73%	80%	75%	86%
93.7%	98%	85%	97%	94%	97%	91%
67.3%	77%	91%	42%	63%	71%	60%
73.3%	84%	80%	55%	81%	70%	70%
48.3%	49%	63%	45%	46%	40%	47%
66.2%	71%	59%	53%	73%	67%	74%
62.0%	61%	68%	41%	66%	61%	75%
63.0%	69%	84%	34%	55%	70%	66%
76.2%	77%	70%	67%	89%	74%	80%
34.3%	33%	46%	22%	38%	25%	42%
83.5%	84%	83%	86%	87%	80%	81%
74.8%	82%	80%	61%	75%	75%	76%
44.7%	46%	59%	32%	45%	43%	43%
85.3%	90%	82%	85%	81%	85%	89%
86.2%	84%	93%	85%	87%	90%	78%
82.8%	82%	81%	84%	81%	91%	78%
62.5%	71%	70%	48%	62%	67%	57%
67.5%	67%	85%	60%	66%	58%	69%
88.0%	89%	86%	85%	91%	85%	92%
73.0%	77%	73%	62%	74%	75%	77%
56.0%	49%	59%	53%	57%	49%	69%
47.5%	61%	64%	33%	58%	20%	49%
63.8%	72%	75%	44%	69%	65%	58%
72.3%	81%	85%	57%	70%	75%	66%
72.5%	82%	76%	68%	76%	58%	75%
75.2%	83%	83%	68%	72%	64%	81%
83.7%	84%	79%	86%	82%	82%	89%
82.8%	90%	84%	77%	86%	79%	81%
73.2%	78%	62%	71%	79%	71%	78%