	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 68.9%	4th 66.4%	5th 65.1%	1st 70.1%	6th 63.4%	3rd 67.4%
68.2%	83%	67%	72%	69%	59%	59%
70.7%	71%	65%	67%	75%	74%	72%
79.5%	83%	92%	82%	88%	66%	66%
57.8%	63%	73%	51%	55%	54%	51%
67.0%	82%	46%	64%	69%	67%	74%
71.7%	68%	73%	68%	75%	74%	72%
78.0%	79%	63%	74%	86%	83%	83%
59.8%	69%	100%	50%	37%	59%	44%
56.2%	60%	68%	47%	58%	50%	54%
80.8%	84%	82%	61%	89%	78%	91%
65.7%	67%	73%	48%	68%	68%	70%
44.7%	46%	30%	43%	49%	49%	51%
43.0%	61%	72%	10%	51%	22%	42%
72.0%	64%	77%	78%	77%	61%	75%
49.5%	48%	45%	57%	54%	36%	57%
75.7%	81%	68%	72%	85%	67%	81%
67.0%	68%	65%	67%	67%	74%	61%
67.3%	68%	46%	72%	71%	75%	72%
61.8%	66%	61%	49%	70%	51%	74%
66.8%	72%	49%	78%	74%	55%	73%
68.5%	67%	65%	79%	74%	56%	70%
76.2%	71%	77%	74%	83%	70%	82%
48.7%	53%	59%	48%	41%	55%	36%
61.8%	67%	60%	61%	63%	60%	60%
44.7%	36%	37%	56%	56%	34%	49%
62.8%	67%	57%	81%	71%	40%	61%
91.3%	93%	88%	93%	92%	86%	96%
75.7%	88%	84%	72%	68%	76%	66%
68.2%	77%	69%	63%	75%	65%	60%
57.0%	60%	54%	48%	75%	39%	66%
48.0%	50%	68%	37%	46%	50%	37%
64.3%	65%	50%	58%	67%	78%	68%
84.3%	89%	91%	69%	91%	75%	91%
73.0%	62%	65%	90%	73%	65%	83%
35.0%	28%	38%	29%	35%	42%	38%
74.0%	78%	69%	68%	79%	79%	71%
80.2%	79%	64%	87%	85%	83%	83%
69.5%	66%	77%	65%	71%	74%	64%
73.2%	69%	71%	64%	83%	82%	70%
54.0%	54%	46%	52%	55%	63%	54%
68.7%	72%	65%	69%	72%	68%	66%
70.7%	74%	70%	67%	70%	70%	73%
80.3%	76%	64%	80%	88%	87%	87%
81.3%	92%	80%	94%	88%	66%	68%
86.0%	89%	96%	76%	87%	77%	91%
62.8%	63%	61%	67%	60%	57%	69%
53.2%	62%	52%	44%	65%	33%	63%
66.2%	70%	82%	52%	66%	72%	55%
83.3%	75%	76%	93%	88%	77%	91%
77.0%	80%	81%	74%	81%	65%	81%
62.2%	68%	56%	77%	66%	45%	61%
76.5%	74%	78%	81%	73%	78%	75%
79.3%	69%	71%	84%	81%	90%	81%
50.7%	53%	50%	52%	50%	47%	52%