	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 67.4%	6th 61.5%	5th 61.7%	2nd 66.9%	3rd 65.0%	4th 64.3%
70.7%	78%	52%	85%	68%	76%	65%
73.0%	87%	68%	79%	87%	65%	52%
81.3%	89%	84%	90%	75%	75%	75%
52.7%	56%	61%	50%	47%	46%	56%
58.2%	65%	20%	77%	56%	63%	68%
57.7%	36%	36%	73%	73%	92%	36%
69.7%	82%	67%	57%	67%	65%	80%
75.8%	78%	100%	61%	69%	69%	78%
49.5%	41%	43%	45%	53%	60%	55%
64.0%	65%	72%	52%	69%	58%	68%
76.0%	82%	68%	49%	90%	81%	86%
55.5%	48%	22%	52%	70%	67%	74%
74.5%	82%	100%	74%	89%	48%	54%
63.7%	77%	41%	75%	70%	45%	74%
71.2%	69%	38%	81%	74%	84%	81%
76.8%	100%	74%	86%	81%	60%	60%
61.2%	72%	39%	61%	73%	62%	60%
67.8%	72%	45%	62%	60%	81%	87%
76.7%	78%	78%	78%	74%	78%	74%
54.3%	66%	43%	59%	57%	47%	54%
56.2%	68%	55%	44%	56%	60%	54%
64.2%	66%	68%	56%	66%	61%	68%
60.0%	76%	84%	59%	55%	40%	46%
55.5%	55%	36%	62%	54%	64%	62%
59.0%	62%	43%	61%	60%	68%	60%
60.8%	64%	56%	67%	60%	64%	54%
67.8%	68%	64%	70%	67%	69%	69%
58.7%	74%	47%	41%	59%	78%	53%
69.7%	71%	84%	48%	73%	84%	58%
78.2%	62%	83%	83%	83%	75%	83%
36.3%	36%	41%	29%	47%	29%	36%
60.0%	65%	73%	51%	74%	31%	66%
50.3%	56%	51%	39%	64%	40%	52%
66.8%	78%	67%	63%	73%	53%	67%
50.5%	61%	78%	55%	47%	28%	34%
63.3%	81%	60%	59%	60%	60%	60%
69.3%	69%	83%	51%	69%	78%	66%
62.0%	57%	71%	57%	71%	58%	58%
52.2%	38%	41%	57%	57%	62%	58%
71.0%	60%	82%	56%	60%	84%	84%
58.0%	62%	47%	61%	60%	60%	58%
59.8%	59%	69%	36%	60%	81%	54%
59.0%	54%	50%	65%	60%	65%	60%
70.3%	78%	48%	67%	69%	82%	78%
63.2%	69%	59%	45%	67%	61%	78%
71.2%	61%	83%	61%	83%	83%	56%
61.0%	75%	75%	52%	60%	50%	54%
61.2%	71%	68%	39%	68%	68%	53%
87.0%	84%	84%	85%	90%	89%	90%
67.5%	65%	64%	74%	66%	66%	70%
76.2%	77%	76%	74%	77%	76%	77%
55.0%	44%	47%	59%	57%	61%	62%
83.2%	77%	88%	91%	61%	91%	91%
67.0%	75%	44%	71%	77%	67%	68%