	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 65.9%	6th 57.2%	3rd 63.6%	5th 60.1%	4th 63.0%
43.8%	47%	42%	39%	49%	46%	40%
59.5%	61%	72%	55%	54%	65%	50%
65.3%	58%	76%	61%	65%	72%	60%
53.3%	56%	64%	33%	51%	61%	55%
71.7%	74%	83%	74%	80%	57%	62%
74.7%	80%	76%	85%	79%	63%	65%
41.7%	42%	43%	35%	48%	34%	48%
61.3%	71%	60%	49%	66%	60%	62%
65.2%	59%	95%	10%	71%	86%	70%
62.8%	71%	67%	68%	55%	53%	63%
64.7%	64%	68%	63%	65%	63%	65%
76.0%	83%	69%	67%	80%	82%	75%
75.3%	86%	75%	72%	71%	70%	78%
77.8%	79%	78%	74%	83%	79%	74%
61.8%	69%	57%	71%	55%	71%	48%
53.3%	61%	59%	26%	63%	52%	59%
67.8%	68%	68%	64%	71%	68%	68%
56.0%	62%	49%	63%	63%	50%	49%
59.7%	56%	66%	58%	65%	59%	54%
38.0%	44%	37%	30%	47%	24%	46%
72.5%	72%	77%	67%	73%	69%	77%
46.2%	43%	54%	36%	45%	52%	47%
64.0%	69%	71%	56%	65%	59%	64%
79.2%	79%	82%	81%	72%	73%	88%
51.2%	43%	52%	53%	45%	56%	58%
61.5%	64%	52%	56%	65%	64%	68%
57.0%	57%	55%	48%	63%	57%	62%
57.2%	45%	60%	55%	61%	61%	61%
68.5%	76%	65%	63%	70%	73%	64%
59.7%	58%	77%	20%	59%	100%	44%
42.8%	38%	49%	37%	38%	39%	56%
58.8%	64%	61%	60%	58%	57%	53%
76.0%	72%	82%	78%	73%	70%	81%
77.0%	85%	67%	75%	75%	75%	85%
46.5%	46%	52%	49%	47%	41%	44%
55.2%	58%	60%	56%	53%	50%	54%
58.0%	58%	53%	57%	61%	61%	58%
63.7%	53%	65%	72%	66%	61%	65%
67.0%	75%	70%	62%	70%	59%	66%
45.2%	54%	52%	30%	50%	49%	36%
67.5%	73%	52%	52%	78%	75%	75%
59.0%	67%	51%	60%	69%	37%	70%
58.2%	59%	71%	54%	63%	42%	60%
50.5%	54%	57%	32%	51%	58%	51%
64.2%	58%	60%	78%	66%	57%	66%
50.2%	56%	67%	37%	54%	46%	41%
70.3%	60%	78%	77%	71%	62%	74%
53.8%	52%	59%	58%	55%	45%	54%
78.5%	79%	74%	79%	88%	64%	87%
68.3%	63%	78%	75%	71%	54%	69%
57.3%	59%	71%	34%	62%	59%	59%
75.5%	80%	76%	81%	72%	70%	74%
72.2%	80%	73%	60%	76%	71%	73%
58.0%	57%	56%	62%	57%	58%	58%
69.0%	72%	67%	62%	77%	65%	71%
60.3%	70%	66%	42%	69%	48%	67%
71.3%	78%	71%	63%	79%	71%	66%
61.7%	75%	75%	52%	49%	69%	50%
68.3%	70%	64%	74%	69%	60%	73%
49.8%	49%	49%	41%	59%	47%	54%
47.5%	55%	53%	31%	42%	64%	40%
62.5%	63%	68%	63%	60%	53%	68%
73.2%	81%	75%	61%	73%	67%	82%
67.8%	60%	67%	75%	72%	60%	73%
70.8%	66%	80%	71%	72%	68%	68%
68.2%	64%	66%	74%	68%	68%	69%
70.7%	69%	67%	72%	75%	66%	75%
75.0%	75%	76%	75%	75%	70%	79%
60.3%	59%	54%	76%	58%	55%	60%
75.3%	65%	70%	89%	70%	68%	90%
75.5%	78%	85%	81%	73%	63%	73%
47.3%	45%	56%	41%	46%	41%	55%
50.5%	52%	58%	38%	47%	62%	46%
46.0%	50%	49%	32%	51%	39%	55%
46.8%	42%	54%	45%	45%	34%	61%
69.0%	69%	60%	66%	70%	79%	70%
74.5%	73%	74%	62%	86%	71%	81%
81.2%	75%	80%	87%	78%	78%	89%
71.0%	73%	72%	54%	66%	84%	77%
56.7%	76%	84%	10%	64%	54%	52%
57.0%	69%	100%	44%	59%	32%	38%
52.2%	63%	69%	33%	47%	50%	51%
34.2%	32%	43%	22%	30%	41%	37%
52.2%	54%	55%	46%	55%	49%	54%
70.8%	69%	70%	63%	76%	68%	79%
55.0%	61%	59%	45%	54%	58%	53%
63.2%	70%	68%	68%	48%	63%	62%
67.5%	75%	67%	66%	70%	56%	71%
84.8%	93%	80%	92%	88%	79%	77%
79.7%	82%	80%	76%	77%	84%	79%
65.5%	80%	79%	68%	64%	49%	53%