	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 63.2%	1st 67.6%	5th 58.1%	2nd 65.2%	6th 57.3%	3rd 64.0%
30.5%	25%	33%	29%	28%	22%	46%
47.5%	49%	52%	33%	42%	64%	45%
45.0%	53%	57%	39%	42%	37%	42%
68.0%	68%	67%	57%	72%	72%	72%
70.7%	69%	82%	51%	70%	81%	71%
54.5%	47%	71%	50%	53%	53%	53%
79.2%	73%	95%	80%	77%	77%	73%
48.0%	46%	33%	46%	54%	47%	62%
54.8%	53%	71%	52%	60%	43%	50%
74.0%	83%	82%	74%	72%	67%	66%
67.2%	65%	85%	70%	69%	50%	64%
55.5%	55%	45%	69%	60%	44%	60%
52.2%	69%	73%	33%	69%	25%	44%
68.7%	69%	69%	57%	69%	74%	74%
59.8%	57%	54%	53%	61%	67%	67%
25.2%	26%	33%	21%	22%	18%	31%
77.2%	83%	80%	70%	79%	72%	79%
60.3%	62%	66%	47%	61%	61%	65%
59.0%	62%	69%	45%	62%	56%	60%
70.0%	75%	79%	79%	73%	41%	73%
72.5%	70%	76%	64%	72%	73%	80%
40.2%	45%	32%	33%	39%	43%	49%
85.3%	82%	88%	86%	77%	88%	91%
70.5%	65%	86%	68%	69%	67%	68%
47.3%	65%	68%	28%	63%	21%	39%
64.7%	60%	73%	79%	73%	41%	62%
79.7%	80%	72%	80%	84%	78%	84%
76.8%	76%	72%	86%	80%	62%	85%
77.0%	88%	89%	10%	91%	98%	86%
42.3%	33%	49%	23%	47%	59%	43%
27.5%	24%	31%	27%	28%	26%	29%
63.3%	63%	66%	67%	63%	58%	63%
67.5%	76%	69%	66%	65%	65%	64%
74.8%	69%	84%	84%	71%	69%	72%
74.8%	71%	82%	77%	79%	63%	77%
81.8%	83%	88%	54%	96%	83%	87%
65.2%	65%	69%	65%	63%	61%	68%
68.3%	71%	79%	66%	71%	58%	65%
59.7%	60%	61%	73%	69%	38%	57%
60.8%	71%	57%	56%	69%	52%	60%
74.2%	74%	74%	89%	73%	62%	73%
67.3%	65%	67%	73%	66%	57%	76%
36.8%	40%	43%	19%	44%	35%	40%
77.3%	76%	84%	73%	86%	67%	78%
72.0%	70%	68%	82%	81%	58%	73%
83.0%	77%	86%	88%	87%	81%	79%