	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 66.6%	2nd 63.7%	6th 58.7%	3rd 63.0%	5th 61.8%	4th 62.9%
66.5%	68%	61%	78%	66%	60%	66%
78.0%	80%	60%	77%	81%	81%	89%
85.3%	84%	100%	89%	90%	74%	75%
55.3%	64%	51%	59%	56%	46%	56%
45.2%	56%	37%	49%	45%	20%	64%
44.8%	45%	45%	37%	43%	50%	49%
75.5%	79%	85%	60%	78%	76%	75%
60.8%	74%	100%	41%	47%	69%	34%
46.5%	52%	40%	37%	48%	55%	47%
61.3%	69%	67%	47%	59%	59%	67%
75.2%	79%	68%	56%	82%	84%	82%
56.2%	61%	24%	58%	64%	64%	66%
70.5%	83%	79%	69%	75%	55%	62%
80.2%	80%	83%	74%	82%	75%	87%
75.0%	77%	74%	84%	77%	63%	75%
80.8%	76%	81%	85%	81%	81%	81%
67.3%	62%	72%	57%	78%	66%	69%
73.2%	75%	60%	74%	76%	77%	77%
58.8%	71%	63%	56%	48%	52%	63%
57.3%	60%	63%	54%	54%	55%	58%
61.2%	62%	60%	57%	60%	64%	64%
57.3%	64%	49%	52%	58%	61%	60%
58.0%	68%	61%	57%	40%	76%	46%
57.2%	59%	35%	62%	62%	64%	61%
61.0%	66%	61%	66%	60%	55%	58%
56.0%	60%	60%	64%	54%	46%	52%
67.7%	68%	60%	69%	67%	73%	69%
59.0%	67%	68%	49%	60%	58%	52%
65.0%	74%	65%	53%	73%	69%	56%
60.0%	65%	64%	61%	56%	50%	64%
51.8%	56%	56%	51%	60%	41%	47%
47.3%	66%	40%	44%	36%	41%	57%
48.0%	57%	47%	33%	46%	55%	50%
68.2%	73%	76%	58%	67%	72%	63%
45.3%	53%	47%	47%	34%	44%	47%
80.0%	66%	90%	65%	81%	95%	83%
59.8%	67%	76%	43%	59%	56%	58%
40.2%	50%	50%	41%	40%	29%	31%
62.0%	54%	66%	63%	61%	67%	61%
51.8%	50%	63%	34%	60%	60%	44%
59.3%	61%	63%	55%	60%	58%	59%
47.2%	61%	54%	33%	36%	58%	41%
60.0%	60%	78%	55%	68%	46%	53%
75.7%	80%	79%	65%	82%	70%	78%
62.5%	65%	53%	53%	67%	68%	69%
66.0%	65%	69%	63%	65%	67%	67%
45.2%	66%	39%	39%	52%	23%	52%
59.3%	66%	76%	43%	64%	60%	47%
86.5%	88%	90%	82%	89%	86%	84%
61.8%	65%	61%	65%	61%	58%	61%
83.5%	82%	87%	85%	80%	78%	89%
63.3%	57%	61%	64%	63%	69%	66%
80.5%	69%	80%	77%	83%	91%	83%
69.0%	73%	41%	83%	68%	68%	81%