	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 67.5%	3rd 64.7%	6th 60.6%	1st 68.2%	5th 60.8%	4th 63.3%
73.0%	72%	73%		73%	73%	74%
48.2%	58%	63%	31%	40%	58%	39%
52.0%	76%	55%	43%	58%	31%	49%
100.0%	100%	100%	100%	100%	100%	100%
52.3%	47%	58%	47%	47%	61%	54%
56.0%	37%	63%	64%	40%	66%	66%
76.7%	71%	75%	82%	79%	80%	73%
47.7%	43%	67%	38%	50%	45%	43%
72.3%	73%	66%	77%	90%	67%	61%
68.3%	76%	77%	70%	66%	56%	65%
74.8%	80%	88%	75%	66%	79%	61%
41.8%	47%	27%	47%	58%	27%	45%
68.3%	72%	88%	79%	76%	35%	60%
100.0%	100%	100%	100%	100%	100%	100%
63.8%	72%	53%	51%	73%	64%	70%
61.5%	66%	60%	63%	62%	60%	58%
76.3%	76%	75%	76%	79%	73%	79%
66.2%	77%	67%	50%	73%	61%	69%
65.0%	79%	50%	53%	73%	65%	70%
51.5%	61%	55%	43%	64%	43%	43%
53.5%	65%	25%	47%	61%	65%	58%
54.7%	52%	51%	56%	65%	44%	60%
83.0%	87%	83%	91%	73%	91%	73%
52.7%	58%	38%	53%	57%	55%	55%
68.3%	72%	88%	79%	76%	35%	60%
58.5%	57%	56%	71%	69%	42%	56%
54.0%	58%	37%	55%	60%	51%	63%
61.3%	70%	51%	56%	73%	51%	67%
74.7%	86%	90%	10%	95%	81%	86%
58.3%	57%	62%	41%	67%	56%	67%
74.0%	78%	77%	71%	75%	66%	77%
80.0%	73%	90%	77%	82%	78%	80%
66.7%	78%	73%	59%	64%	61%	65%
65.2%	60%	63%	64%	68%	68%	68%
52.3%	50%	57%	55%	54%	49%	49%
57.2%	50%	70%	65%	50%	54%	54%
73.8%	83%	73%	77%	83%	61%	66%
48.8%	49%	44%	46%	44%	55%	55%
48.0%	61%	43%	34%	64%	43%	43%
67.3%	76%	49%	61%	77%	77%	64%
76.2%	77%	73%	87%	77%	70%	73%
44.8%	36%	51%	43%	45%	59%	35%
61.7%	68%	77%	38%	67%	60%	60%
66.3%	70%	65%	59%	74%	56%	74%
60.0%	62%	56%	60%	62%	60%	60%
77.5%	91%	73%	81%	90%	65%	65%