	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 71.4%	1st 73.4%	6th 59.0%	3rd 70.0%	5th 62.8%	4th 68.6%
39.8%	33%	45%		38%	29%	54%
71.2%	74%	84%		63%	74%	61%
61.2%	70%	72%		55%	55%	54%
71.0%	74%	67%		68%	73%	73%
62.3%	61%	77%	46%	60%	69%	61%
67.4%	54%	74%		71%	71%	67%
81.4%	85%	68%		83%	83%	88%
62.0%	61%	67%		61%	64%	57%
65.0%	68%	74%	66%	64%	63%	55%
86.0%	96%	96%		80%	73%	85%
63.0%	71%	76%		64%	46%	58%
54.8%	52%	55%		60%	42%	65%
63.0%	74%	82%		71%	31%	57%
68.8%	74%	68%	53%	74%	71%	73%
57.0%	52%	54%		57%	63%	59%
48.2%	42%	66%		42%	38%	53%
70.6%	69%	77%		72%	65%	70%
78.0%	75%	82%		79%	77%	77%
78.4%	82%	84%		78%	74%	74%
60.0%	66%	71%		65%	37%	61%
70.6%	67%	74%		73%	67%	72%
65.8%	74%	51%		66%	59%	79%
92.6%	98%	92%		96%	87%	90%
77.0%	79%	83%		76%	68%	79%
58.8%	71%	74%		67%	28%	54%
61.8%	58%	67%		60%	56%	68%
74.8%	74%	69%	75%	79%	76%	76%
80.0%	76%	78%		90%	68%	88%
96.2%	99%	99%		98%	95%	90%
62.5%	71%	69%	33%	69%	68%	65%
47.6%	47%	50%		46%	39%	56%
76.7%	80%	78%	74%	80%	70%	78%
67.4%	75%	73%		65%	57%	67%
79.2%	78%	84%		80%	78%	76%
78.0%	87%	82%		83%	65%	73%
90.2%	96%	92%		79%	92%	92%
67.0%	71%	69%		68%	63%	64%
70.4%	71%	77%		75%	61%	68%
58.6%	63%	64%		71%	37%	58%
91.0%	98%	95%		92%	83%	87%
70.0%	77%	72%		68%	66%	67%
66.8%	69%	70%		63%	75%	57%
55.8%	56%	60%		57%	57%	49%
58.0%	54%	62%	66%	64%	46%	56%
82.4%	88%	88%		86%	66%	84%
65.2%	75%	65%		64%	62%	60%