	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 64.5%	1st 66.4%	6th 55.3%	3rd 63.5%	5th 60.3%	4th 61.5%
68.2%	69%	64%	74%	72%	67%	63%
75.7%	74%	75%	77%	81%	72%	75%
91.0%	95%	92%	94%	92%	86%	87%
54.7%	66%	59%	48%	52%	52%	51%
55.5%	65%	43%	54%	54%	43%	74%
61.2%	67%	62%	38%	67%	75%	58%
60.3%	72%	62%	39%	64%	65%	60%
57.7%	75%	86%	45%	45%	45%	50%
49.0%	52%	59%	48%	44%	41%	50%
49.0%	48%	61%	29%	48%	61%	47%
84.8%	84%	94%	69%	85%	88%	89%
84.5%	79%	90%	81%	86%	86%	85%
43.7%	61%	73%	10%	53%	27%	38%
65.3%	67%	63%	57%	65%	75%	65%
82.7%	85%	72%	89%	82%	86%	82%
88.0%	88%	97%	83%	89%	88%	83%
52.3%	55%	60%	42%	58%	50%	49%
68.7%	67%	84%	64%	74%	64%	59%
38.7%	39%	48%	30%	46%	20%	49%
64.3%	67%	79%	60%	54%	62%	64%
62.2%	61%	62%	56%	59%	66%	69%
72.2%	84%	73%	56%	75%	74%	71%
43.3%	48%	45%	49%	27%	57%	34%
63.7%	65%	51%	71%	64%	64%	67%
71.8%	71%	73%	62%	71%	81%	73%
77.3%	83%	86%	67%	85%	60%	83%
90.0%	90%	79%	91%	96%	94%	90%
55.2%	68%	67%	41%	51%	61%	43%
72.0%	80%	80%	54%	78%	70%	70%
45.8%	39%	54%	50%	49%	28%	55%
71.7%	74%	77%	64%	66%	79%	70%
48.5%	44%	42%	42%	60%	47%	56%
44.8%	48%	55%	29%	46%	44%	47%
64.3%	62%	63%	63%	66%	62%	70%
24.3%	21%	27%	21%	30%	24%	23%
85.0%	79%	89%	90%	80%	86%	86%
66.2%	74%	72%	51%	67%	72%	61%
25.3%	28%	28%	21%	29%	24%	22%
76.5%	77%	75%	74%	79%	77%	77%
63.2%	56%	75%	66%	57%	69%	56%
74.2%	74%	83%	67%	75%	84%	62%
54.2%	60%	68%	35%	48%	66%	48%
45.0%	39%	57%	40%	42%	46%	46%
73.3%	80%	77%	83%	76%	64%	60%
79.3%	75%	84%	64%	88%	77%	88%
29.7%	26%	38%	36%	30%	7%	41%
32.7%	39%	28%	25%	51%	17%	36%
49.2%	63%	55%	29%	51%	51%	46%
50.3%	55%	70%	33%	47%	48%	49%
57.2%	54%	58%	55%	68%	42%	66%
74.0%	83%	78%	74%	72%	64%	73%
64.5%	67%	57%	62%	64%	69%	68%
82.8%	91%	84%	79%	93%	73%	77%
58.7%	52%	52%	56%	77%	57%	58%