	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 64.3%	1st 65.4%	6th 54.5%	3rd 63.1%	5th 59.4%	4th 61.5%
66.2%	76%	64%	74%	68%	54%	61%
75.3%	72%	68%	77%	78%	72%	85%
92.7%	95%	95%	94%	92%	88%	92%
54.2%	66%	62%	49%	52%	46%	50%
53.3%	61%	34%	53%	52%	43%	77%
58.5%	67%	62%	40%	67%	57%	58%
62.0%	72%	65%	39%	61%	72%	63%
56.3%	73%	86%	45%	47%	37%	50%
47.2%	52%	64%	36%	46%	43%	42%
47.8%	48%	55%	29%	48%	61%	46%
82.8%	81%	90%	69%	85%	83%	89%
80.8%	78%	68%	81%	90%	86%	82%
44.7%	61%	66%	10%	53%	38%	40%
67.8%	63%	67%	57%	65%	81%	74%
79.0%	85%	74%	79%	72%	82%	82%
89.0%	88%	93%	83%	93%	88%	89%
51.3%	52%	61%	42%	58%	50%	45%
66.7%	67%	84%	69%	64%	57%	59%
40.2%	42%	48%	30%	52%	20%	49%
64.7%	67%	80%	63%	67%	47%	64%
59.3%	61%	62%	39%	59%	66%	69%
73.8%	85%	85%	56%	74%	72%	71%
40.0%	43%	41%	49%	27%	46%	34%
63.3%	65%	49%	71%	64%	64%	67%
73.0%	71%	73%	69%	71%	81%	73%
79.8%	83%	82%	67%	86%	78%	83%
86.7%	90%	79%	90%	88%	91%	82%
53.7%	65%	66%	41%	46%	61%	43%
69.3%	80%	67%	54%	80%	65%	70%
47.8%	46%	54%	50%	48%	34%	55%
73.0%	74%	86%	58%	74%	81%	65%
48.7%	44%	41%	42%	60%	47%	58%
46.8%	50%	61%	29%	46%	48%	47%
64.5%	63%	65%	63%	64%	64%	68%
23.8%	21%	30%	21%	30%	18%	23%
82.7%	79%	89%	90%	87%	77%	74%
63.3%	75%	66%	51%	59%	68%	61%
26.5%	28%	28%	21%	35%	25%	22%
74.8%	77%	71%	74%	75%	79%	73%
64.2%	56%	75%	66%	63%	69%	56%
70.7%	74%	83%	62%	65%	78%	62%
52.3%	60%	56%	34%	48%	68%	48%
45.3%	38%	57%	40%	45%	46%	46%
73.0%	80%	76%	78%	76%	68%	60%
79.8%	77%	88%	64%	85%	77%	88%
29.8%	26%	33%	38%	25%	7%	50%
30.8%	39%	28%	19%	51%	12%	36%
49.5%	56%	55%	29%	48%	58%	51%
51.2%	55%	69%	33%	51%	50%	49%
54.3%	54%	58%	50%	60%	42%	62%
73.5%	83%	75%	74%	72%	64%	73%
64.5%	67%	57%	65%	64%	69%	65%
84.2%	91%	90%	79%	88%	73%	84%
59.5%	52%	52%	56%	82%	57%	58%