	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 69.0%	5th 62.4%	- -	2nd 66.3%	4th 63.6%	3rd 64.9%
35.0%	31%	59%		32%	32%	21%
49.0%	40%	100%		35%	35%	35%
60.2%	58%	55%		64%	62%	62%
68.8%	71%	64%		68%	71%	70%
80.0%	88%	93%		80%	54%	85%
62.6%	73%	49%		66%	58%	67%
58.8%	62%	40%		68%	68%	56%
72.6%	74%	73%		72%	66%	78%
72.2%	74%	84%		59%	85%	59%
73.8%	84%	80%		68%	65%	72%
66.8%	60%	68%		72%	72%	62%
59.0%	70%	78%		47%	57%	43%
85.8%	93%	100%		76%	74%	86%
53.4%	65%	80%		68%	27%	27%
58.0%	61%	84%		42%	61%	42%
57.4%	58%	52%		64%	55%	58%
57.8%	61%	44%		62%	60%	62%
58.8%	73%	48%		61%	57%	55%
69.6%	84%	71%		85%	54%	54%
65.4%	71%	80%		46%	69%	61%
68.8%	82%	42%		80%	65%	75%
77.4%	82%	79%		69%	75%	82%
65.2%	70%	78%		65%	48%	65%
70.2%	78%	38%		76%	77%	82%
27.4%	23%	48%		24%	19%	23%
76.6%	88%	59%		61%	91%	84%
81.8%	85%	89%		72%	89%	74%
73.0%	80%	100%		63%	61%	61%
67.0%	76%	45%		68%	74%	72%
66.8%	80%	80%		64%	62%	48%
69.0%	80%	64%		80%	69%	52%
67.6%	73%	36%		76%	80%	73%
69.8%	65%	65%		73%	80%	66%
66.4%	63%	61%		81%	53%	74%
71.6%	71%	54%		76%	78%	79%
71.8%	70%	77%		72%	68%	72%
71.4%	78%	37%		84%	84%	74%
66.0%	68%	23%		80%	70%	89%
73.6%	77%	77%		80%	65%	69%
63.6%	68%	73%		55%	73%	49%
72.8%	82%	75%		61%	82%	64%
61.6%	85%	30%		46%	83%	64%
66.6%	68%	81%		68%	55%	61%
64.0%	69%	64%		54%	65%	68%
57.0%	56%	63%		56%	47%	63%
58.8%	56%	68%		64%	46%	60%
81.2%	89%	58%		91%	77%	91%
40.2%	41%	0%		52%	56%	52%
71.6%	72%	50%		80%	83%	73%
42.6%	43%	43%		39%	34%	54%
49.0%	55%	35%		51%	51%	53%
66.0%	70%	77%		64%	61%	58%
74.2%	80%	70%		68%	63%	90%
64.4%	69%	74%		60%	58%	61%
83.2%	72%	72%		80%	100%	92%
62.6%	58%	90%		73%	40%	52%
50.6%	74%	41%		64%	27%	47%
63.6%	73%	61%		70%	62%	52%
46.8%	68%	67%		65%	17%	17%
78.2%	83%	68%		73%	89%	78%
74.2%	89%	73%		62%	89%	58%
76.0%	69%	77%		66%	77%	91%
48.8%	41%	44%		41%	65%	53%
62.8%	60%	21%		74%	76%	83%
46.4%	80%	47%		35%	35%	35%
64.6%	74%	21%		75%	68%	85%
67.2%	67%	69%		65%	68%	67%
74.6%	78%	48%		81%	87%	79%
75.4%	80%	90%		80%	61%	66%
50.4%	0%	41%		66%	67%	78%
52.6%	71%	38%		67%	36%	51%
65.0%	73%	58%		59%	65%	70%
37.2%	34%	58%		36%	23%	35%
67.2%	76%	32%		76%	84%	68%
66.4%	68%	69%		57%	69%	69%
86.8%	99%	88%		91%	79%	77%
100.0%	100%	100%		100%	100%	100%
48.4%	43%	36%		49%	61%	53%
70.0%	76%	50%		85%	60%	79%
52.8%	61%	80%		64%	18%	41%
85.4%	69%	100%		100%	58%	100%
74.0%	71%	63%		80%	80%	76%
57.6%	60%	52%		58%	64%	54%
63.6%	65%	62%		63%	64%	64%
76.6%	80%	71%		72%	86%	74%
62.4%	63%	61%		60%	56%	72%
69.2%	65%	41%		73%	79%	88%
47.6%	50%	43%		47%	49%	49%
81.2%	85%	90%		85%	73%	73%
76.2%	84%	72%		78%	69%	78%
72.2%	80%	70%		76%	60%	75%