	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 81.2%	5th 74.6%	- -	1st 81.4%	4th 76.3%	3rd 78.3%
72.6%	79%	83%		69%	69%	63%
63.2%	61%	67%		69%	55%	64%
79.4%	82%	67%		89%	78%	81%
79.2%	89%	74%		70%	81%	82%
63.4%	72%	64%		59%	59%	63%
77.6%	71%	86%		72%	71%	88%
71.0%	87%	63%		69%	75%	61%
68.4%	60%	47%		84%	75%	76%
73.0%	75%	54%		84%	75%	77%
78.6%	60%	91%		67%	83%	92%
75.4%	91%	44%		88%	74%	80%
87.2%	88%	91%		92%	75%	90%
78.8%	77%	76%		79%	86%	76%
62.8%	84%	57%		66%	54%	53%
70.2%	62%	59%		78%	84%	68%
80.0%	89%	76%		90%	68%	77%
81.0%	83%	84%		78%	81%	79%
80.6%	83%	83%		83%	80%	74%
88.4%	89%	88%		91%	87%	87%
84.6%	90%	77%		85%	84%	87%
79.2%	88%	76%		87%	77%	68%
83.0%	92%	86%		86%	71%	80%
73.0%	66%	83%		68%	63%	85%
66.2%	77%	77%		60%	51%	66%
74.4%	84%	49%		80%	83%	76%
92.4%	84%	95%		93%	95%	95%
82.4%	85%	88%		85%	77%	77%
79.0%	82%	81%		81%	80%	71%
80.8%	89%	85%		81%	81%	68%
83.4%	84%	91%		85%	79%	78%
80.8%	82%	83%		79%	71%	89%
77.8%	75%	80%		81%	70%	83%
76.6%	77%	85%		78%	80%	63%
78.0%	84%	71%		90%	67%	78%
82.4%	76%	83%		81%	85%	87%
76.4%	78%	78%		71%	71%	84%
83.8%	88%	78%		85%	78%	90%
79.4%	79%	80%		76%	83%	79%
85.8%	81%	87%		93%	79%	89%
80.0%	73%	78%		83%	88%	78%
80.2%	94%	53%		88%	78%	88%
74.0%	79%	78%		72%	73%	68%
75.6%	72%	64%		89%	82%	71%
83.8%	84%	88%		83%	78%	86%
82.6%	86%	80%		83%	83%	81%
83.8%	78%	83%		89%	80%	89%
77.0%	86%	82%		74%	64%	79%
87.0%	93%	73%		89%	86%	94%
84.0%	94%	80%		85%	84%	77%
87.0%	92%	84%		90%	88%	81%
84.6%	91%	87%		86%	79%	80%
56.6%	64%	40%		62%	60%	57%
75.4%	82%	85%		81%	55%	74%
76.8%	78%	78%		79%	77%	72%
83.2%	79%	80%		90%	87%	80%
77.4%	81%	75%		76%	76%	79%
57.8%	60%	59%		61%	40%	69%
88.6%	90%	90%		89%	89%	85%
66.0%	74%	70%		74%	54%	58%
80.8%	83%	85%		79%	78%	79%
75.8%	80%	61%		92%	73%	73%
75.8%	84%	82%		63%	78%	72%
90.4%	91%	89%		96%	81%	95%
75.4%	80%	47%		86%	78%	86%
67.0%	66%	81%		65%	52%	71%
74.8%	86%	57%		80%	73%	78%
74.8%	81%	88%		74%	72%	59%
75.8%	80%	62%		85%	72%	80%
70.2%	79%	71%		67%	62%	72%
91.6%	97%	85%		95%	90%	91%
83.6%	87%	84%		83%	81%	83%
77.6%	87%	48%		89%	83%	81%
74.8%	80%	43%		90%	73%	88%
66.8%	73%	79%		69%	44%	69%
82.6%	86%	83%		83%	79%	82%
75.6%	77%	53%		84%	81%	83%
85.0%	82%	86%		92%	79%	86%
79.2%	84%	71%		87%	75%	79%
72.2%	82%	47%		82%	73%	77%
77.0%	80%	72%		81%	76%	76%
91.2%	90%	84%		96%	90%	96%
85.8%	89%	83%		93%	79%	85%
72.2%	81%	55%		79%	73%	73%
85.4%	89%	90%		80%	88%	80%
81.0%	85%	80%		85%	77%	78%
72.4%	84%	47%		84%	71%	76%
82.2%	85%	78%		90%	71%	87%
78.0%	77%	79%		81%	81%	72%
80.4%	89%	79%		85%	67%	82%
84.6%	93%	85%		92%	75%	78%
72.6%	65%	91%		68%	75%	64%
70.8%	64%	63%		90%	69%	68%
72.4%	81%	53%		74%	80%	74%
82.0%	84%	90%		81%	80%	75%
79.2%	83%	78%		79%	78%	78%
80.0%	74%	77%		84%	80%	85%
80.8%	79%	57%		90%	88%	90%
80.0%	81%	48%		89%	92%	90%
74.6%	74%	79%		75%	77%	68%
83.4%	90%	74%		88%	75%	90%
67.2%	66%	58%		68%	64%	80%
91.6%	91%	90%		83%	97%	97%
73.4%	77%	76%		62%	82%	70%
81.2%	75%	79%		84%	87%	81%
84.0%	85%	88%		82%	83%	82%
81.6%	88%	74%		80%	87%	79%
75.8%	79%	70%		88%	72%	70%
71.2%	65%	74%		84%	65%	68%
75.6%	73%	78%		77%	77%	73%
73.2%	84%	47%		88%	78%	69%
83.6%	86%	78%		81%	87%	86%
88.2%	84%	92%		90%	87%	88%
87.6%	83%	88%		91%	95%	81%
83.2%	89%	83%		86%	75%	83%
84.2%	95%	80%		87%	84%	75%
84.6%	85%	86%		86%	80%	86%