	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 64.2%	1st 66.2%	6th 55.2%	3rd 63.3%	5th 60.4%	4th 61.7%
67.2%	67%	64%	74%	68%	67%	63%
72.2%	73%	68%	77%	74%	60%	81%
91.5%	95%	95%	94%	92%	86%	87%
54.5%	66%	58%	49%	52%	52%	50%
54.7%	65%	42%	53%	46%	43%	79%
61.3%	67%	63%	38%	67%	75%	58%
60.7%	72%	65%	39%	58%	68%	62%
58.8%	75%	86%	45%	45%	52%	50%
50.5%	54%	61%	48%	46%	44%	50%
44.8%	48%	55%	29%	44%	47%	46%
82.7%	84%	84%	69%	87%	83%	89%
81.3%	79%	67%	81%	90%	86%	85%
42.5%	61%	75%	10%	53%	18%	38%
67.5%	64%	67%	57%	65%	78%	74%
80.5%	85%	74%	79%	74%	89%	82%
87.3%	88%	93%	83%	85%	88%	87%
52.5%	54%	61%	42%	58%	50%	50%
69.2%	75%	84%	64%	69%	64%	59%
37.5%	39%	48%	30%	52%	11%	45%
66.3%	67%	79%	63%	63%	62%	64%
61.8%	61%	62%	56%	53%	70%	69%
74.2%	85%	84%	56%	75%	74%	71%
41.5%	43%	50%	49%	27%	46%	34%
65.7%	65%	59%	75%	68%	64%	63%
73.3%	71%	76%	69%	71%	80%	73%
79.3%	77%	86%	67%	85%	78%	83%
88.2%	90%	79%	90%	91%	94%	85%
52.5%	58%	66%	41%	43%	61%	46%
71.7%	80%	67%	54%	82%	77%	70%
49.2%	46%	54%	50%	56%	34%	55%
68.2%	73%	55%	58%	74%	79%	70%
50.8%	44%	42%	41%	60%	60%	58%
46.2%	48%	55%	29%	51%	47%	47%
65.0%	64%	62%	63%	70%	61%	70%
27.8%	21%	40%	21%	30%	32%	23%
87.0%	78%	89%	90%	89%	90%	86%
64.3%	75%	72%	51%	59%	68%	61%
28.2%	28%	42%	21%	28%	28%	22%
75.7%	77%	71%	74%	76%	79%	77%
65.3%	56%	75%	66%	63%	76%	56%
68.3%	74%	81%	62%	62%	69%	62%
52.2%	60%	63%	35%	44%	67%	44%
45.5%	38%	57%	40%	46%	46%	46%
74.0%	80%	78%	83%	75%	68%	60%
77.8%	77%	84%	64%	81%	73%	88%
33.7%	26%	38%	41%	42%	7%	48%
37.5%	39%	54%	25%	51%	12%	44%
48.8%	61%	55%	30%	47%	60%	40%
51.0%	55%	70%	33%	51%	48%	49%
52.5%	51%	54%	50%	68%	30%	62%
73.2%	78%	78%	74%	72%	64%	73%
64.5%	67%	57%	65%	64%	69%	65%
82.2%	91%	80%	79%	93%	73%	77%
59.7%	53%	52%	56%	82%	57%	58%