	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 66.9%	1st 69.9%	6th 57.0%	3rd 66.4%	4th 65.8%	5th 63.7%
70.5%	80%	75%	51%	72%	75%	70%
77.5%	72%	77%	80%	81%	78%	77%
77.5%	71%	83%	80%	80%	77%	74%
36.7%	34%	38%	46%	30%	23%	49%
82.8%	84%	74%	82%	84%	89%	84%
54.0%	59%	65%	41%	52%	60%	47%
58.7%	56%	64%	59%	60%	67%	46%
50.7%	53%	55%	27%	51%	71%	47%
66.3%	68%	75%	46%	68%	72%	69%
35.3%	30%	36%	32%	44%	26%	44%
82.5%	86%	88%	84%	73%	86%	78%
29.2%	29%	34%	20%	34%	25%	33%
73.7%	80%	79%	61%	70%	76%	76%
79.8%	81%	82%	78%	79%	89%	70%
86.7%	89%	87%	86%	88%	82%	88%
66.0%	76%	85%	48%	63%	62%	62%
53.7%	61%	65%	47%	59%	45%	45%
50.3%	58%	56%	30%	53%	55%	50%
53.2%	64%	41%	48%	58%	48%	60%
62.5%	54%	74%	63%	66%	62%	56%
66.5%	74%	68%	43%	70%	83%	61%
75.7%	78%	81%	56%	76%	87%	76%
62.2%	69%	70%	58%	60%	45%	71%
69.8%	72%	70%	58%	71%	74%	74%
84.8%	80%	82%	84%	93%	90%	80%
74.3%	76%	81%	61%	79%	75%	74%
51.3%	60%	60%	32%	46%	60%	50%
60.5%	72%	71%	40%	65%	64%	51%
32.7%	37%	34%	24%	40%	18%	43%
42.7%	37%	49%	41%	45%	41%	43%
81.0%	83%	83%	78%	80%	82%	80%
84.0%	94%	76%	80%	85%	83%	86%
65.5%	54%	79%	67%	67%	64%	62%
65.8%	63%	87%	58%	64%	65%	58%
35.0%	40%	29%	29%	33%	34%	45%
66.8%	74%	80%	54%	73%	67%	53%
84.8%	88%	89%	79%	85%	82%	86%
83.3%	91%	75%	87%	88%	84%	75%
69.5%	67%	78%	52%	72%	81%	67%
93.0%	83%	99%	98%	92%	94%	92%
59.8%	58%	83%	45%	63%	56%	54%
67.2%	67%	67%	57%	69%	73%	70%
68.5%	75%	80%	60%	75%	60%	61%