	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 70.7%	1st 72.1%	6th 62.3%	3rd 70.0%	5th 63.1%	4th 68.9%
39.3%	33%	46%	39%	38%	29%	51%
67.7%	74%	74%	53%	65%	78%	62%
59.0%	70%	67%	54%	49%	55%	59%
68.2%	74%	67%	53%	74%	68%	73%
61.3%	61%	73%	46%	58%	69%	61%
68.8%	59%	77%	64%	71%	71%	71%
80.3%	84%	66%	78%	84%	82%	88%
59.5%	61%	66%	47%	60%	66%	57%
66.2%	68%	76%	64%	65%	61%	63%
83.3%	96%	91%	78%	80%	70%	85%
63.3%	68%	77%	67%	64%	46%	58%
56.3%	52%	57%	71%	52%	41%	65%
58.2%	74%	79%	39%	69%	31%	57%
69.8%	74%	67%	58%	74%	73%	73%
56.3%	53%	54%	45%	57%	63%	66%
44.3%	42%	49%	37%	51%	38%	49%
70.8%	73%	72%	73%	72%	65%	70%
72.7%	75%	74%	60%	73%	77%	77%
73.7%	82%	78%	56%	78%	74%	74%
66.2%	66%	73%	72%	72%	61%	53%
69.5%	67%	75%	63%	71%	67%	74%
61.2%	71%	49%	50%	67%	58%	72%
94.0%	98%	92%	97%	96%	91%	90%
79.0%	79%	89%	73%	80%	74%	79%
54.7%	71%	75%	35%	65%	28%	54%
66.0%	58%	67%	83%	68%	52%	68%
74.7%	76%	69%	75%	79%	73%	76%
79.8%	74%	77%	89%	83%	67%	89%
81.0%	99%	99%	10%	98%	90%	90%
63.0%	71%	77%	33%	64%	68%	65%
48.3%	44%	55%	51%	46%	39%	55%
76.2%	79%	77%	74%	80%	69%	78%
67.0%	75%	73%	64%	65%	61%	64%
73.8%	70%	61%	77%	76%	76%	83%
76.2%	80%	80%	85%	75%	64%	73%
89.0%	96%	93%	82%	79%	92%	92%
68.5%	71%	69%	70%	68%	65%	68%
69.5%	69%	80%	62%	77%	61%	68%
60.2%	61%	69%	65%	71%	37%	58%
91.5%	98%	98%	86%	97%	83%	87%
69.3%	77%	72%	64%	70%	66%	67%
69.2%	69%	72%	69%	67%	74%	64%
50.7%	56%	57%	36%	53%	57%	45%
58.3%	54%	64%	66%	64%	46%	56%
80.8%	77%	79%	88%	91%	66%	84%
65.0%	75%	64%	65%	64%	62%	60%