	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 74.9%	1st 75.3%	6th 65.1%	3rd 72.3%	5th 68.2%	4th 69.9%
61.7%	77%	61%	63%	60%	57%	52%
83.7%	85%	87%	86%	82%	71%	91%
88.8%	93%	97%	92%	97%	76%	78%
80.0%	89%	89%	73%	80%	70%	79%
60.7%	71%	47%	51%	58%	59%	78%
60.3%	59%	59%	49%	72%	61%	62%
76.2%	80%	83%	57%	80%	85%	72%
57.7%	78%	94%	35%	39%	63%	37%
68.2%	71%	71%	60%	74%	64%	69%
65.3%	66%	74%	54%	60%	74%	64%
81.7%	85%	81%	66%	89%	91%	78%
83.5%	80%	72%	89%	80%	88%	92%
55.3%	69%	85%	56%	60%	19%	43%
87.5%	90%	86%	88%	89%	83%	89%
86.7%	91%	87%	87%	89%	83%	83%
83.8%	85%	90%	90%	78%	73%	87%
75.7%	80%	82%	65%	82%	80%	65%
74.5%	78%	91%	70%	72%	61%	75%
43.5%	59%	48%	35%	45%	27%	47%
76.7%	79%	85%	65%	76%	87%	68%
81.2%	81%	88%	68%	84%	88%	78%
76.2%	86%	85%	64%	76%	73%	73%
61.3%	64%	59%	66%	46%	81%	52%
71.2%	76%	70%	75%	67%	70%	69%
87.5%	88%	85%	92%	88%	84%	88%
85.7%	93%	89%	85%	86%	78%	83%
88.8%	84%	85%	76%	97%	95%	96%
62.0%	71%	69%	49%	57%	70%	56%
79.3%	87%	83%	69%	85%	77%	75%
49.8%	55%	56%	48%	57%	31%	52%
75.0%	79%	75%	53%	82%	75%	86%
58.5%	64%	53%	47%	56%	63%	68%
66.8%	68%	70%	53%	66%	78%	66%
77.7%	76%	81%	67%	80%	80%	82%
30.0%	36%	34%	21%	34%	23%	32%
86.8%	80%	95%	92%	85%	90%	79%
70.3%	75%	73%	54%	72%	77%	71%
41.0%	41%	44%	36%	41%	43%	41%
83.2%	81%	82%	89%	89%	82%	76%
76.0%	74%	83%	74%	76%	87%	62%
79.7%	79%	86%	76%	78%	87%	72%
68.5%	77%	74%	53%	67%	78%	62%
59.3%	51%	80%	51%	64%	56%	54%
80.0%	84%	85%	84%	93%	61%	73%
73.3%	72%	73%	62%	80%	74%	79%
52.8%	58%	55%	53%	49%	35%	67%
42.2%	60%	51%	32%	48%	17%	45%
52.2%	56%	63%	32%	57%	57%	48%
73.7%	83%	83%	62%	74%	66%	74%
67.8%	72%	81%	68%	77%	35%	74%
83.2%	90%	86%	89%	80%	70%	84%
81.7%	83%	75%	84%	84%	82%	82%
84.5%	79%	80%	87%	88%	82%	91%
72.0%	77%	66%	71%	81%	64%	73%