	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 69.3%	1st 69.6%	6th 57.5%	3rd 66.3%	5th 62.3%	4th 65.1%
71.0%	83%	75%	41%	80%	77%	70%
83.5%	82%	72%	84%	84%	88%	91%
78.0%	75%	73%	87%	81%	77%	75%
34.3%	36%	30%	33%	31%	34%	42%
81.3%	81%	84%	87%	83%	69%	84%
69.2%	81%	81%	52%	64%	64%	73%
62.8%	64%	71%	62%	62%	60%	58%
67.0%	82%	85%	36%	65%	68%	66%
84.8%	92%	89%	68%	88%	83%	89%
39.2%	41%	56%	44%	37%	9%	48%
83.7%	84%	89%	87%	76%	88%	78%
30.3%	36%	44%	21%	36%	9%	36%
72.8%	85%	75%	59%	76%	66%	76%
88.7%	95%	89%	86%	87%	91%	84%
67.7%	65%	72%	54%	68%	77%	70%
55.7%	63%	66%	41%	52%	60%	52%
51.8%	61%	74%	38%	46%	46%	46%
55.8%	65%	65%	36%	58%	61%	50%
63.5%	72%	49%	61%	72%	60%	67%
60.3%	55%	75%	58%	61%	58%	55%
71.3%	89%	80%	40%	72%	75%	72%
76.3%	75%	87%	53%	81%	84%	78%
76.7%	77%	75%	76%	83%	65%	84%
68.5%	79%	66%	59%	77%	59%	71%
58.5%	61%	62%	57%	59%	55%	57%
65.5%	63%	65%	69%	62%	60%	74%
57.2%	63%	69%	37%	51%	68%	55%
45.0%	54%	68%	33%	33%	49%	33%
34.2%	38%	39%	25%	50%	7%	46%
58.2%	56%	57%	58%	66%	59%	53%
72.0%	80%	78%	58%	72%	72%	72%
73.8%	79%	73%	67%	73%	72%	79%
55.8%	53%	53%	63%	58%	55%	53%
76.2%	79%	84%	73%	78%	79%	64%
52.7%	63%	32%	65%	52%	32%	72%
70.3%	77%	87%	54%	82%	69%	53%
71.8%	66%	71%	72%	72%	80%	70%
86.8%	85%	80%	84%	90%	94%	88%
47.8%	58%	56%	36%	46%	45%	46%
93.3%	89%	94%	99%	98%	91%	89%
63.5%	70%	83%	53%	63%	62%	50%
51.0%	51%	56%	42%	54%	47%	56%
67.8%	77%	64%	63%	73%	56%	74%