	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 70.9%	1st 71.3%	6th 61.3%	3rd 67.5%	5th 64.4%	4th 66.8%
77.0%	85%	68%	91%	81%	68%	69%
71.8%	72%	65%	72%	71%	72%	79%
87.3%	88%	87%	88%	92%	83%	86%
54.5%	65%	63%	42%	50%	49%	58%
53.7%	76%	21%	64%	59%	21%	81%
63.0%	80%	80%	86%	43%	43%	46%
67.3%	67%	86%	47%	67%	65%	72%
59.2%	68%	86%	57%	25%	67%	52%
49.2%	51%	66%	29%	54%	45%	50%
61.8%	68%	66%	42%	69%	65%	61%
79.7%	73%	87%	61%	88%	85%	84%
77.3%	78%	57%	83%	81%	82%	83%
55.2%	61%	86%	41%	62%	43%	38%
72.8%	74%	79%	57%	64%	83%	80%
79.7%	79%	77%	80%	72%	86%	84%
86.7%	86%	85%	80%	89%	89%	91%
51.7%	55%	59%	43%	58%	45%	50%
67.8%	67%	76%	69%	76%	55%	64%
80.3%	79%	77%	83%	80%	86%	77%
70.5%	61%	80%	61%	66%	84%	71%
64.2%	59%	72%	46%	59%	86%	63%
81.0%	93%	85%	61%	87%	82%	78%
45.0%	54%	59%	41%	27%	56%	33%
62.2%	71%	20%	75%	68%	68%	71%
69.0%	70%	72%	66%	70%	62%	74%
78.2%	89%	84%	64%	83%	60%	89%
86.2%	78%	90%	87%	94%	85%	83%
60.5%	63%	82%	46%	48%	76%	48%
75.0%	84%	79%	60%	83%	74%	70%
83.0%	84%	84%	86%	86%	80%	78%
32.3%	26%	66%	23%	35%	17%	27%
65.7%	66%	64%	52%	70%	57%	85%
56.2%	68%	48%	42%	69%	55%	55%
65.0%	63%	68%	64%	65%	61%	69%
54.0%	52%	51%	53%	48%	76%	44%
88.3%	80%	90%	89%	92%	87%	92%
65.7%	78%	76%	53%	66%	62%	59%
55.3%	51%	57%	47%	57%	61%	59%
73.8%	72%	75%	75%	77%	71%	73%
66.5%	70%	75%	67%	61%	59%	67%
71.5%	81%	70%	72%	78%	60%	68%
57.8%	70%	70%	37%	54%	67%	49%
60.8%	64%	75%	45%	59%	61%	61%
61.5%	70%	58%	78%	54%	58%	51%
77.7%	88%	86%	58%	87%	57%	90%
77.5%	81%	70%	86%	78%	80%	70%
61.8%	79%	78%	66%	57%	37%	54%
52.8%	60%	93%	28%	39%	53%	44%
64.3%	70%	70%	64%	68%	51%	63%
55.0%	51%	57%	55%	58%	37%	72%
76.7%	83%	81%	72%	81%	66%	77%
63.3%	61%	64%	59%	67%	63%	66%
83.5%	91%	89%	66%	92%	82%	81%
63.0%	77%	42%	52%	80%	57%	70%