	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 70.0%	3rd 68.0%	6th 63.8%	1st 71.7%	5th 64.6%	4th 67.9%
83.5%	72%	100%	84%	79%	79%	87%
74.5%	74%	73%	66%	80%	77%	77%
55.2%	62%	58%	51%	62%	47%	51%
100.0%	100%	100%	100%	100%	100%	100%
65.7%	53%	77%	65%	64%	65%	70%
59.0%	57%	59%	58%	58%	63%	59%
69.3%	72%	60%	79%	65%	62%	78%
38.2%	28%	74%	29%	37%	31%	30%
65.0%	72%	76%	62%	82%	49%	49%
66.7%	71%	86%	58%	62%	56%	67%
58.2%	59%	74%	54%	64%	46%	52%
59.2%	68%	57%	57%	69%	45%	59%
80.2%	100%	94%	54%	100%	52%	81%
100.0%	100%	100%	100%	100%	100%	100%
52.0%	45%	57%	50%	62%	47%	51%
81.3%	74%	83%	84%	87%	83%	77%
79.3%	87%	76%	85%	76%	76%	76%
76.5%	76%	77%	74%	76%	75%	81%
69.0%	68%	71%	67%	68%	67%	73%
45.7%	57%	36%	45%	60%	38%	38%
67.7%	71%	66%	72%	66%	61%	70%
56.3%	76%	26%	60%	61%	48%	67%
93.7%	96%	100%	78%	94%	100%	94%
65.8%	74%	51%	63%	67%	69%	71%
79.5%	94%	88%	59%	94%	56%	86%
43.3%	45%	52%	47%	52%	26%	38%
61.5%	64%	27%	61%	65%	74%	78%
44.5%	55%	10%	47%	62%	40%	53%
72.7%	82%	88%	10%	94%	82%	80%
62.7%	64%	57%	58%	66%	64%	67%
76.3%	77%	79%	73%	75%	79%	75%
57.2%	60%	57%	54%	61%	56%	55%
68.0%	64%	73%	61%	64%	79%	67%
83.7%	95%	67%	87%	81%	82%	90%
78.0%	79%	81%	78%	66%	81%	83%
45.3%	45%	52%	39%	47%	41%	48%
70.7%	76%	78%	73%	72%	58%	67%
69.8%	76%	55%	70%	66%	82%	70%
51.7%	54%	47%	44%	66%	53%	46%
66.5%	67%	61%	65%	77%	63%	66%
76.8%	73%	76%	80%	80%	76%	76%
69.7%	68%	65%	76%	75%	75%	59%
58.7%	63%	64%	46%	67%	64%	48%
54.5%	53%	56%	46%	67%	50%	55%
73.5%	71%	73%	79%	73%	74%	71%
86.2%	84%	89%	86%	89%	80%	89%