	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 70.9%	5th 66.0%	4th 68.5%	1st 73.0%	6th 65.3%	3rd 69.5%
63.3%	65%	73%	62%	67%	46%	67%
58.5%	65%	35%	68%	64%	46%	73%
70.5%	63%	57%	72%	77%	77%	77%
70.8%	82%	89%	64%	64%	64%	62%
83.2%	83%	93%	71%	82%	87%	83%
89.3%	89%	75%	92%	89%	92%	99%
83.7%	89%	75%	83%	87%	84%	84%
75.3%	85%	75%	52%	84%	84%	72%
78.2%	83%	80%	78%	76%	73%	79%
68.0%	73%	64%	64%	64%	79%	64%
74.7%	75%	79%	80%	77%	70%	67%
74.5%	77%	70%	80%	69%	79%	72%
81.8%	85%	77%	93%	90%	59%	87%
49.0%	55%	50%	48%	63%	39%	39%
69.5%	67%	63%	82%	82%	50%	73%
70.8%	79%	60%	73%	79%	60%	74%
69.5%	83%	76%	54%	83%	54%	67%
53.0%	56%	69%	31%	52%	60%	50%
39.8%	34%	63%	36%	33%	34%	39%
79.2%	73%	77%	81%	80%	80%	84%
72.2%	70%	60%	77%	80%	69%	77%
64.7%	57%	39%	81%	74%	66%	71%
51.7%	51%	63%	53%	53%	36%	54%
71.0%	64%	79%	64%	76%	67%	76%
52.8%	52%	59%	54%	78%	37%	37%
69.8%	68%	70%	75%	68%	65%	73%
53.5%	61%	54%	52%	60%	38%	56%
70.2%	79%	60%	59%	72%	79%	72%
71.0%	79%	83%	72%	56%	68%	68%
66.2%	69%	77%	57%	67%	61%	66%
61.0%	50%	49%	74%	69%	62%	62%
56.0%	61%	72%	56%	51%	45%	51%
71.2%	67%	57%	72%	77%	77%	77%
78.8%	83%	62%	81%	87%	80%	80%
57.8%	67%	31%	73%	53%	61%	62%
63.2%	67%	37%	71%	66%	70%	68%
68.7%	60%	62%	76%	86%	56%	72%
86.3%	94%	86%	83%	94%	84%	77%
58.2%	59%	38%	65%	65%	55%	67%
91.7%	100%	89%	94%	89%	89%	89%
77.2%	76%	68%	74%	82%	85%	78%
60.8%	66%	66%	41%	74%	56%	62%
84.7%	88%	77%	77%	100%	83%	83%