	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 71.2%	5th 60.6%	3rd 61.4%	2nd 63.2%	6th 59.4%	4th 61.2%
63.6%		87%	48%	68%	72%	43%
44.6%		68%	27%	46%	39%	43%
52.6%		62%	51%	48%	58%	44%
53.2%		44%	61%	55%	55%	51%
32.6%		30%	37%	30%	22%	44%
77.8%		47%	84%	82%	90%	86%
59.8%		74%	58%	59%	57%	51%
77.8%		63%	88%	77%	80%	81%
62.0%		37%	65%	48%	79%	81%
69.2%		67%	75%	74%	65%	65%
81.8%		89%	81%	79%	85%	75%
75.4%		87%	82%	82%	49%	77%
76.0%		81%	77%	77%	77%	68%
43.6%		29%	44%	58%	43%	44%
50.2%		22%	56%	56%	63%	54%
52.0%		68%	48%	52%	41%	51%
87.2%		90%	90%	90%	78%	88%
49.0%	44%	57%	49%	42%	51%	51%
71.5%	71%	61%	79%	87%	54%	77%
55.2%		58%	37%	58%	60%	63%
64.5%	76%	68%	64%	68%	40%	71%
55.6%		16%	66%	68%	64%	64%
68.8%		61%	75%	70%	70%	68%
42.0%		74%	40%	34%	31%	31%
61.6%		77%	64%	58%	58%	51%
67.4%		68%	65%	68%	68%	68%
41.2%		38%	41%	48%	38%	41%
65.6%		77%	56%	61%	77%	57%
44.7%	48%	51%	41%	44%	51%	33%
55.8%		49%	65%	66%	29%	70%
82.0%		88%	83%	67%	86%	86%
63.6%		66%	63%	66%	62%	61%
63.8%		75%	60%	67%	68%	49%
50.0%		63%	48%	57%	41%	41%
78.8%		78%	75%	73%	84%	84%
65.0%		79%	71%	49%	63%	63%
55.4%		64%	48%	48%	47%	70%
66.4%		61%	59%	77%	68%	67%
56.4%		29%	64%	65%	63%	61%
60.6%		46%	55%	68%	68%	66%
69.6%		48%	84%	49%	93%	74%
35.4%		30%	51%	37%	37%	22%
70.6%		79%	77%	73%	62%	62%
60.0%		60%	52%	56%	63%	69%
67.0%		63%	60%	68%	72%	72%
66.2%		67%	42%	83%	66%	73%
49.4%		66%	40%	47%	49%	45%
92.6%		88%	85%	90%	100%	100%
45.8%		10%	60%	60%	42%	57%
46.8%		50%	51%	44%	42%	47%
54.2%		56%	56%	49%	57%	53%
44.6%		30%	59%	39%	46%	49%
50.0%		45%	59%	52%	41%	53%
53.4%		74%	48%	48%	48%	49%
58.0%		56%	62%	61%	56%	55%
47.4%		61%	50%	50%	38%	38%
51.6%		51%	41%	49%	41%	76%
55.8%		57%	58%	58%	53%	53%
66.6%		73%	67%	69%	62%	62%
42.8%		13%	57%	48%	48%	48%
62.0%		74%	57%	67%	66%	46%
58.2%		68%	47%	62%	67%	47%
63.6%		74%	70%	63%	50%	61%
48.0%		41%	57%	46%	52%	44%
74.0%		71%	77%	77%	74%	71%
59.8%		54%	69%	63%	53%	60%
49.0%		73%	40%	49%	49%	34%
54.6%		58%	58%	63%	45%	49%
62.6%		56%	62%	70%	60%	65%
74.8%		69%	78%	72%	74%	81%
69.4%		73%	74%	67%	68%	65%
68.2%		58%	71%	73%	73%	66%
71.6%		54%	78%	74%	76%	76%
47.6%		44%	48%	53%	40%	53%
66.4%		72%	66%	66%	62%	66%
73.2%		70%	78%	76%	68%	74%
73.6%		58%	85%	80%	64%	81%
56.8%		70%	57%	58%	33%	66%
56.0%		66%	59%	57%	56%	42%
56.6%		56%	62%	54%	56%	55%
70.8%		78%	68%	69%	69%	70%
83.8%	80%	89%	79%	89%	77%	89%
77.3%	81%	84%	78%	78%	73%	70%
63.8%		62%	66%	67%	62%	62%
46.0%		51%	55%	51%	25%	48%
59.0%		35%	73%	65%	61%	61%
53.0%		56%	50%	53%	46%	60%
66.0%		58%	75%	68%	60%	69%
48.4%		77%	36%	55%	31%	43%
72.6%		83%	77%	77%	51%	75%
46.6%		74%	36%	36%	51%	36%
43.2%		76%	14%	59%	38%	29%
74.8%		51%	60%	88%	100%	75%
69.8%	80%	55%	69%	73%	70%	72%
51.0%		31%	60%	56%	54%	54%
73.2%		71%	76%	73%	73%	73%
55.0%		32%	60%	66%	56%	61%
70.8%		62%	74%	73%	72%	73%
68.0%		66%	50%	74%	74%	76%
69.2%		56%	74%	67%	69%	80%
48.8%		30%	55%	49%	49%	61%
78.8%	74%	86%	77%	80%	68%	88%
67.6%		76%	72%	65%	73%	52%
71.4%		69%	72%	72%	72%	72%
74.8%	87%	77%	71%	79%	59%	76%
63.8%		33%	57%	87%	87%	55%
50.6%		88%	31%	60%	33%	41%
43.0%		62%	25%	46%	39%	43%
62.0%		58%	56%	57%	66%	73%
58.4%		66%	60%	58%	58%	50%
60.8%		49%	74%	61%	59%	61%
68.6%		40%	76%	78%	75%	74%
73.0%		68%	68%	88%	68%	73%
58.4%		45%	65%	65%	61%	56%
70.8%		90%	71%	68%	51%	74%
69.6%		63%	73%	76%	62%	74%