	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%	5th 65.7%	3rd 69.5%	1st 70.6%	6th 63.8%	4th 68.3%
77.8%	73%	68%	83%	81%	81%	81%
50.3%	48%	38%	52%	48%	53%	63%
79.8%	77%	69%	82%	86%	86%	79%
81.5%	77%	76%	91%	78%	78%	89%
77.0%	78%	84%	84%	71%	69%	76%
67.7%	64%	65%	67%	67%	67%	76%
65.5%	68%	73%	66%	63%	63%	60%
76.2%	85%	85%	62%	78%	78%	69%
66.8%	65%	72%	58%	72%	65%	69%
73.2%	74%	75%	72%	75%	78%	65%
78.0%	80%	83%	89%	76%	64%	76%
64.7%	65%	64%	65%	65%	64%	65%
62.3%	69%	44%	76%	68%	45%	72%
50.7%	58%	46%	47%	53%	53%	47%
74.8%	73%	83%	82%	79%	57%	75%
65.5%	60%	60%	68%	65%	71%	69%
72.0%	83%	87%	71%	72%	50%	69%
54.5%	57%	78%	35%	53%	53%	51%
34.2%	28%	64%	16%	41%	28%	28%
54.8%	68%	41%	63%	63%	41%	53%
61.2%	63%	35%	77%	68%	50%	74%
76.7%	77%	68%	91%	84%	55%	85%
79.8%	68%	91%	86%	77%	79%	78%
56.8%	73%	50%	61%	60%	39%	58%
57.2%	62%	55%	62%	62%	56%	46%
47.2%	51%	55%	47%	41%	41%	48%
65.2%	75%	56%	64%	64%	68%	64%
75.8%	83%	40%	79%	90%	84%	79%
70.0%	79%	67%	64%	68%	73%	69%
64.2%	63%	81%	57%	68%	60%	56%
64.5%	67%	60%	74%	72%	48%	66%
48.5%	53%	59%	47%	38%	44%	50%
80.0%	77%	69%	82%	87%	86%	79%
70.0%	79%	72%	71%	83%	56%	59%
61.7%	63%	47%	77%	71%	63%	49%
69.3%	71%	31%	78%	77%	74%	85%
84.2%	85%	82%	86%	89%	77%	86%
55.5%	57%	72%	61%	55%	43%	45%
89.7%	92%	78%	100%	91%	77%	100%
89.2%	85%	78%	91%	98%	95%	88%
69.5%	77%	57%	66%	77%	74%	66%
76.8%	85%	74%	54%	89%	70%	89%
82.5%	74%	91%	86%	72%	86%	86%