	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 70.1%	6th 67.0%	3rd 70.0%	1st 71.4%	5th 68.0%	4th 69.6%
77.3%	76%	76%	73%	81%	81%	77%
47.0%	48%	19%	50%	60%	49%	56%
78.2%	71%	69%	82%	82%	86%	79%
75.7%	77%	73%	78%	75%	78%	73%
78.8%	78%	84%	86%	78%	71%	76%
72.7%	67%	69%	71%	73%	84%	72%
74.0%	70%	76%	70%	76%	76%	76%
68.5%	69%	71%	56%	77%	74%	64%
65.2%	62%	58%	60%	73%	65%	73%
75.8%	65%	78%	78%	78%	78%	78%
81.0%	83%	76%	84%	83%	83%	77%
63.3%	63%	69%	65%	65%	64%	54%
60.0%	66%	58%	61%	68%	35%	72%
66.3%	68%	66%	68%	70%	62%	64%
81.0%	84%	79%	80%	79%	75%	89%
66.0%	65%	63%	66%	65%	71%	66%
66.5%	83%	63%	62%	72%	50%	69%
49.0%	58%	69%	34%	46%	53%	34%
31.5%	28%	64%	27%	28%	26%	16%
72.5%	60%	76%	72%	75%	76%	76%
74.5%	78%	70%	91%	70%	56%	82%
78.0%	84%	61%	84%	85%	62%	92%
79.7%	72%	92%	90%	72%	74%	78%
55.7%	65%	52%	55%	61%	36%	65%
61.8%	65%	73%	61%	61%	56%	55%
53.3%	57%	57%	60%	56%	41%	49%
71.0%	75%	82%	70%	64%	68%	67%
77.2%	84%	51%	79%	84%	86%	79%
72.7%	79%	80%	63%	73%	77%	64%
61.7%	60%	81%	57%	60%	56%	56%
70.0%	68%	64%	72%	72%	64%	80%
50.0%	53%	59%	47%	47%	44%	50%
79.2%	77%	69%	82%	82%	86%	79%
73.7%	85%	49%	80%	76%	76%	76%
67.5%	58%	47%	72%	68%	89%	71%
73.3%	75%	43%	84%	73%	80%	85%
80.8%	86%	60%	85%	86%	83%	85%
57.3%	56%	72%	69%	55%	43%	49%
83.2%	92%	64%	91%	91%	84%	77%
86.8%	74%	78%	91%	95%	95%	88%
67.3%	75%	58%	71%	77%	66%	57%
74.2%	70%	74%	52%	85%	82%	82%
81.8%	84%	87%	81%	72%	81%	86%