	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 64.5%	4th 63.5%	3rd 64.3%	1st 65.2%	6th 57.8%	5th 61.3%
59.5%	70%	59%	63%	59%	59%	47%
52.2%	57%	56%	48%	57%	49%	46%
61.5%	60%	78%	65%	56%	48%	62%
53.0%	59%	69%	52%	48%	43%	47%
69.0%	59%	70%	83%	76%	55%	71%
70.3%	82%	41%	84%	82%	70%	63%
54.7%	58%	62%	55%	50%	47%	56%
60.0%	72%	100%	44%	44%	56%	44%
53.0%	54%	66%	55%	52%	40%	51%
62.3%	71%	66%	58%	66%	59%	54%
83.2%	89%	78%	71%	91%	84%	86%
54.7%	57%	25%	57%	69%	59%	61%
54.8%	61%	79%	56%	63%	26%	44%
55.2%	55%	56%	61%	59%	38%	62%
49.3%	49%	39%	60%	59%	38%	51%
66.2%	72%	76%	61%	74%	59%	55%
65.3%	66%	77%	57%	71%	62%	59%
67.3%	70%	67%	71%	74%	54%	68%
71.0%	75%	75%	77%	74%	58%	67%
65.3%	70%	65%	66%	63%	66%	62%
72.5%	72%	64%	79%	75%	75%	70%
64.5%	61%	52%	78%	63%	63%	70%
35.8%	50%	56%	38%	19%	26%	26%
70.0%	76%	52%	69%	76%	74%	73%
53.7%	55%	17%	65%	59%	59%	67%
64.3%	67%	51%	79%	79%	39%	71%
87.5%	88%	91%	95%	79%	79%	93%
66.8%	76%	55%	62%	76%	70%	62%
64.2%	61%	79%	47%	79%	57%	62%
78.2%	58%	86%	86%	67%	86%	86%
42.3%	35%	79%	22%	46%	26%	46%
61.7%	67%	66%	52%	62%	62%	61%
53.2%	56%	62%	50%	56%	49%	46%
62.3%	66%	51%	63%	59%	63%	72%
71.3%	71%	89%	79%	71%	71%	47%
71.5%	73%	91%	67%	68%	60%	70%
70.8%	67%	58%	81%	77%	66%	76%
53.2%	55%	60%	62%	52%	61%	29%
73.3%	66%	66%	73%	79%	80%	76%
63.0%	75%	69%	64%	70%	45%	55%
60.5%	61%	57%	61%	60%	64%	60%
60.0%	50%	62%	69%	66%	54%	59%
63.8%	59%	60%	77%	66%	59%	62%
60.2%	69%	38%	85%	61%	54%	54%
88.7%	87%	91%	68%	91%	100%	95%
74.8%	63%	75%	70%	86%	86%	69%
49.2%	62%	54%	46%	51%	46%	36%
70.2%	67%	79%	70%	70%	64%	71%
81.2%	73%	69%	81%	86%	86%	92%
66.0%	61%	79%	80%	56%	44%	76%
39.0%	48%	33%	41%	51%	20%	41%
61.5%	69%	49%	64%	59%	66%	62%
47.0%	47%	56%	47%	44%	44%	44%
60.2%	67%	31%	56%	76%	55%	76%