	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 67.7%	1st 69.0%	5th 58.5%	3rd 67.2%	6th 58.4%	4th 63.1%
32.8%	32%	33%	28%	34%	31%	39%
48.0%	56%	57%	31%	39%	58%	47%
46.3%	68%	73%	25%	41%	33%	38%
96.0%	96%	96%	96%	96%	96%	96%
48.5%	36%	53%	42%	51%	50%	59%
43.7%	26%	50%	47%	33%	53%	53%
81.8%	90%	92%	79%	80%	75%	75%
64.3%	61%	48%	57%	66%	75%	79%
52.7%	53%	72%	44%	74%	28%	45%
73.7%	83%	85%	60%	75%	71%	68%
71.5%	83%	88%	70%	72%	55%	61%
59.3%	67%	58%	57%	72%	48%	54%
57.7%	57%	76%	83%	56%	21%	53%
96.0%	96%	96%	96%	96%	96%	96%
64.0%	66%	65%	53%	68%	66%	66%
33.2%	34%	37%	30%	36%	31%	31%
72.7%	71%	74%	68%	78%	70%	75%
62.7%	66%	76%	48%	54%	67%	65%
56.5%	63%	71%	41%	56%	55%	53%
68.2%	80%	71%	76%	79%	42%	61%
71.8%	69%	80%	68%	68%	66%	80%
47.0%	60%	35%	36%	41%	61%	49%
86.3%	82%	93%	89%	77%	93%	84%
71.3%	75%	84%	68%	68%	60%	73%
53.0%	52%	71%	77%	51%	19%	48%
71.0%	74%	79%	77%	78%	57%	61%
73.7%	77%	52%	75%	87%	75%	76%
76.8%	86%	86%	71%	79%	66%	73%
77.5%	88%	89%	10%	91%	98%	89%
39.5%	56%	47%	27%	29%	36%	42%
27.5%	30%	10%	28%	42%	29%	26%
63.5%	67%	67%	67%	68%	59%	53%
66.0%	76%	74%	55%	68%	65%	58%
72.7%	79%	84%	79%	84%	38%	72%
75.0%	71%	78%	79%	84%	68%	70%
83.5%	86%	86%	65%	95%	82%	87%
62.8%	72%	67%	59%	68%	61%	50%
66.5%	75%	73%	60%	78%	48%	65%
58.8%	76%	61%	48%	72%	38%	58%
58.7%	70%	57%	50%	68%	52%	55%
66.8%	67%	77%	62%	83%	55%	57%
69.3%	74%	70%	65%	66%	69%	72%
39.0%	41%	44%	21%	40%	48%	40%
75.3%	73%	80%	63%	83%	67%	86%
76.0%	81%	74%	73%	83%	71%	74%
85.0%	73%	86%	90%	85%	85%	91%