	Claude 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4
Score	10th 74.8%	6th 75.5%	1st 78.0%	2nd 76.8%	16th 71.9%	21st 67.3%	3rd 76.4%	4th 75.8%	11th 74.7%	9th 74.8%	7th 75.0%	17th 71.4%	8th 74.9%	12th 73.1%	18th 71.0%	5th 75.8%	14th 72.3%	19th 70.0%	13th 73.0%	15th 72.0%	20th 68.7%
76.5%		67%	80%	79%	61%	64%	84%	81%	82%	79%	79%	81%	81%	80%	84%	81%	74%	62%	75%	77%	79%
67.5%		67%	75%	79%	28%	70%	64%	71%	55%	74%	75%	72%	67%	70%	75%	77%	63%	62%	69%	78%	59%
58.0%		61%	67%	55%	55%	10%	63%	63%	57%	69%	71%	59%	57%	67%	55%	61%	61%	59%	57%	57%	55%
80.8%	91%	78%	91%	79%	88%	66%	83%	83%	89%	78%	81%	74%	91%	84%	85%	83%	64%	75%	75%	74%	85%
76.1%		83%	86%	86%	74%	91%	81%	65%	72%	72%	77%	70%	76%	82%	88%	77%	76%	64%	77%	72%	52%
86.5%		87%	82%	88%	88%	90%	90%	93%	87%	88%	88%	80%	93%	93%	75%	83%	98%	91%	88%	71%	77%
80.1%		71%	78%	82%	73%	79%	76%	81%	78%	75%	76%	89%	78%	83%	84%	89%	83%	83%	78%	91%	75%
75.9%		74%	70%	73%	79%	60%	83%	81%	80%	73%	79%	80%	73%	68%	87%	84%	80%	78%	68%	71%	77%
70.6%		77%	74%	74%	84%	77%	77%	80%	84%	71%	67%	73%	74%	71%	56%	60%	62%	73%	75%	56%	47%
74.3%	74%	80%	77%	78%	74%	74%	66%	73%	74%	78%	74%	74%	74%	74%	76%	78%	69%	68%	74%	74%	78%
61.4%		64%	76%	73%	57%	70%	76%	73%	61%	52%	64%	65%	56%	56%	62%	50%	44%	26%	77%	53%	73%
85.2%	72%	88%	95%	86%	88%	84%	100%	87%	89%	86%	83%	78%	80%	81%	95%	86%	89%	90%	77%	89%	66%
69.3%		67%	73%	78%	59%	85%	68%	65%	71%	68%	77%	62%	66%	73%	72%	72%	82%	44%	78%	67%	59%
66.6%		67%	59%	68%	64%	71%	69%	68%	62%	65%	69%	66%	65%	75%	73%	68%	68%	61%	57%	61%	76%
77.2%		74%	82%	79%	82%	74%	80%	73%	76%	72%	82%	73%	79%	73%	81%	82%	68%	78%	82%	73%	80%
75.8%		77%	79%	67%	86%	70%	79%	80%	71%	82%	76%	74%	77%	72%	82%	73%	74%	81%	69%		72%
76.9%		79%	82%	83%	83%	80%	77%	73%	76%	76%	78%	69%	68%	76%	80%	80%	73%	71%	80%	80%	74%
73.3%		72%	77%	80%	85%	55%	66%	77%	73%	66%	67%	82%	72%	64%	79%	75%	79%	79%	61%	79%	78%
56.7%	64%	45%	61%	55%	56%	45%	63%	76%	57%	69%	61%	39%	67%	59%	64%	69%	55%	47%	46%	46%	46%
68.9%	79%	75%	79%	74%	69%	66%	72%	66%	63%	73%	61%	61%	68%	61%	73%	74%	64%	65%	67%	62%	75%
79.0%		89%	92%	78%	84%	81%	83%	76%	88%	83%	90%	76%	88%	89%	63%	76%	59%	64%	82%	78%	61%
74.3%		82%	79%	82%	73%	81%	80%	69%	77%	82%	76%	65%	72%	78%	78%	75%	56%	63%	80%	74%	64%
73.1%	65%	67%	66%	63%	86%	95%	82%	86%	74%	83%	82%	73%	79%	82%	65%	62%	58%	51%	82%	64%	71%
69.0%		80%	76%	80%	59%	74%	56%	61%	66%	74%	77%	44%	69%	65%	83%	74%	64%	76%	74%	64%	64%
73.6%		74%	71%	70%	73%	76%	75%	76%	76%	70%	72%	74%	74%	75%	76%	79%	74%	74%	70%	74%	69%
71.5%		81%	81%	69%	71%	79%	70%	71%	74%	79%	76%	67%	71%	78%	66%	71%	67%	60%	75%	72%	52%
72.1%		72%	79%	77%	76%	50%	83%	81%	71%	76%	59%	82%	68%	62%	76%	70%	72%	61%	66%	77%	84%
78.5%		81%	78%	78%	58%	71%	84%	83%	77%	79%	86%	79%	84%	72%	80%	79%	87%	80%	70%	84%	80%
59.5%	69%	72%	75%	78%	69%	54%	64%	56%	64%	57%	55%	58%	56%	51%	0%	69%	56%	59%	64%	60%	64%
72.4%		77%	69%	76%	78%	71%	59%	75%	75%	67%	73%	67%	70%	73%	72%	75%	69%	79%	73%	80%	69%
69.8%		74%	71%	70%	67%	73%	76%	67%	70%	74%	73%	65%	74%	69%	73%	71%	67%	57%	67%	64%	73%
86.2%		95%	89%	98%	98%	10%	94%	93%	100%	88%	85%	98%	100%	89%	0%	96%	96%	98%	100%	100%	96%
58.1%		61%	67%	55%	55%	10%	63%	63%	57%	69%	71%	59%	57%	67%	65%	61%	61%	55%	57%	55%	53%
75.8%	86%	74%	77%	85%	64%	62%	73%	83%	80%	83%	73%	72%	75%	61%	82%	83%	87%	82%	68%	61%	80%
75.3%	76%	78%	83%	87%	43%	77%	76%	76%	76%	64%	82%	75%	76%	76%	82%	77%	77%	77%	71%	78%	75%
72.6%		79%	91%	75%	56%	89%	93%	76%	71%	73%	75%	78%	85%	78%	0%	80%	86%	65%	77%	81%	44%
60.4%		63%	65%	64%	57%	59%	62%	61%	62%	61%	57%	59%	62%	56%	59%	64%	61%	57%	61%		58%
81.8%		84%	94%	92%	80%	94%	92%	94%	92%	94%	87%	72%	92%	82%	83%	83%	73%	88%	85%	38%	38%
79.1%		81%	83%	79%	84%	80%	84%	81%	81%	82%	75%	80%	81%	69%	83%	81%	81%	72%	66%	82%	77%
90.4%		95%	89%	98%	98%	10%	94%	93%	100%	88%	85%	98%	100%	89%	100%	96%	96%	98%	100%	98%	83%
76.0%		80%	81%	84%	68%	72%	76%	79%	77%	80%	71%	54%	84%	69%	84%	82%	70%	76%	70%	84%	79%
69.0%	72%	76%	64%	64%	71%	53%	71%	72%	66%	59%	80%	75%	54%	70%	76%	65%	75%	79%	71%	71%	65%
83.6%		78%	92%	85%	92%	90%	80%	78%	81%	86%	81%	81%	89%	82%	80%	87%	90%	82%	81%	84%	73%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.