	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 83.1%	4th 81.1%	1st 85.0%	3rd 81.2%	5th 76.9%	6th 76.3%
57.2%	63%	53%		63%	59%	48%
82.8%	92%	87%		85%	75%	75%
84.2%	89%	88%		89%	74%	81%
75.8%	82%	78%		72%	70%	77%
66.0%	88%	51%		68%	56%	67%
74.6%	86%	85%		83%	70%	49%
89.2%	90%	91%		91%	87%	87%
40.4%	67%	0%		38%	56%	41%
67.2%	72%	55%		76%	60%	73%
83.2%	87%	83%		87%	81%	78%
84.6%	79%	87%		84%	85%	88%
84.4%	84%	77%		85%	87%	89%
59.2%	69%	79%		61%	44%	43%
87.8%	91%	84%		92%	83%	89%
85.8%	86%	90%		88%	81%	84%
85.4%	91%	89%		91%	84%	72%
78.0%	77%	87%		80%	72%	74%
85.4%	92%	94%		86%	74%	81%
82.6%	83%	94%		72%	89%	75%
83.2%	86%	86%		84%	83%	77%
88.6%	86%	88%		90%	89%	90%
90.2%	90%	96%		90%	90%	85%
57.0%	63%	60%		44%	72%	46%
83.6%	80%	88%		85%	81%	84%
86.7%	82%	86%	85%	89%	87%	91%
89.6%	96%	93%		89%	77%	93%
93.0%	90%	87%		100%	94%	94%
75.0%	82%	89%		76%	69%	59%
83.8%	88%	83%		86%	80%	82%
89.8%	86%	91%		90%	91%	91%
53.4%	47%	70%		57%	41%	52%
79.6%	86%	74%		81%	73%	84%
84.6%	88%	80%		84%	88%	83%
83.2%	83%	84%		88%	78%	83%
60.8%	68%	66%		62%	56%	52%
83.6%	88%	91%		82%	80%	77%
82.4%	85%	88%		86%	78%	75%
82.0%	83%	75%		87%	84%	81%
85.6%	76%	89%		95%	82%	86%
88.0%	85%	88%		87%	90%	90%
79.8%	84%	80%		79%	75%	81%
77.2%	84%	88%		66%	78%	70%
77.0%	84%	89%		82%	59%	71%
89.8%	96%	94%		92%	94%	73%
83.6%	88%	81%		79%	84%	86%
88.0%	83%	93%		90%	91%	83%
68.6%	83%	73%		63%	72%	52%
68.2%	74%	68%		68%	67%	64%
84.8%	90%	89%		85%	80%	80%
78.0%	64%	88%		80%	80%	78%
87.6%	96%	91%		92%	72%	87%
88.2%	89%	81%		97%	88%	86%
91.2%	92%	84%		95%	91%	94%
85.0%	94%	75%		94%	72%	90%