	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 75.5%	5th 71.6%	3rd 73.7%	1st 76.4%	6th 69.5%	4th 73.5%
76.2%	75%	80%	62%	77%	81%	82%
61.0%	54%	22%	73%	71%	79%	67%
68.0%	65%	73%	70%	73%	57%	70%
76.5%	73%	86%	74%	74%	74%	78%
79.2%	77%	81%	91%	77%	74%	75%
85.8%	82%	88%	78%	88%	88%	91%
81.8%	83%	83%	76%	88%	78%	83%
76.3%	79%	71%	66%	82%	78%	82%
69.8%	77%	79%	72%	67%	67%	57%
77.7%	81%	74%	85%	74%	74%	78%
62.5%	70%	70%	70%	65%	58%	42%
83.0%	77%	90%	82%	86%	78%	85%
73.5%	76%	83%	82%	75%	49%	76%
73.0%	74%	70%	81%	71%	76%	66%
76.8%	81%	77%	77%	82%	63%	81%
72.3%	77%	69%	64%	74%	75%	75%
78.5%	75%	84%	78%	83%	69%	82%
66.0%	67%	79%	50%	64%	73%	63%
47.0%	40%	73%	34%	50%	38%	47%
69.5%	73%	72%	73%	69%	59%	71%
79.2%	74%	68%	90%	88%	69%	86%
72.2%	74%	66%	82%	77%	57%	77%
80.0%	67%	85%	85%	82%	74%	87%
61.7%	73%	65%	71%	62%	38%	61%
71.7%	76%	68%	75%	73%	70%	68%
72.8%	83%	53%	75%	80%	67%	79%
66.0%	74%	73%	46%	59%	77%	67%
75.0%	79%	62%	79%	80%	76%	74%
62.7%	72%	71%	62%	61%	55%	55%
70.3%	78%	67%	65%	73%	67%	72%
69.3%	71%	73%	73%	73%	58%	68%
89.8%	92%	88%	86%	87%	100%	86%
64.0%	62%	55%	70%	73%	57%	67%
81.5%	89%	60%	79%	90%	81%	90%
67.3%	78%	43%	77%	88%	57%	61%
77.2%	81%	53%	85%	86%	80%	78%
60.3%	64%	63%	56%	62%	61%	56%
83.5%	84%	84%	94%	89%	68%	82%
74.3%	84%	57%	76%	84%	72%	73%
92.2%	95%	98%	86%	85%	100%	89%
71.3%	80%	68%	64%	82%	57%	77%
74.7%	81%	68%	64%	80%	78%	77%
82.7%	78%	86%	90%	81%	81%	80%