	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	15th 69.3%	8th 71.9%	3rd 72.9%	5th 72.2%	19th 67.2%	21st 65.6%	12th 70.7%	9th 71.6%	14th 69.7%	4th 72.6%	10th 70.9%	20th 66.1%	7th 72.2%	18th 67.3%	1st 73.6%	2nd 73.2%	11th 70.8%	16th 69.0%	17th 68.2%	6th 72.2%	13th 70.0%
71.0%		71%	78%	78%	55%	74%	79%	80%	63%	74%	77%	80%	77%	61%	72%	72%	64%	53%	64%	78%	69%
70.7%		77%	77%	77%	64%	79%	77%	84%	70%	68%	77%	56%	77%	62%	73%	62%	62%	60%	79%	73%	60%
81.5%		89%	78%	78%	59%	100%	85%	73%	59%	89%	78%	84%	59%	100%	89%	89%	84%	100%	59%	89%	89%
70.9%	77%	77%	80%	77%	61%	61%	75%	91%	72%	84%	61%	61%	61%	64%	86%	84%	59%	55%	61%	61%	80%
83.6%		92%	88%	88%	81%	81%	86%	73%	92%	89%	81%	81%	81%	81%	86%	86%	92%	81%	81%	81%	71%
76.8%		74%	74%	74%	93%	86%	73%	88%	74%	71%	78%	71%	83%	78%	71%	74%	73%	71%	78%	78%	74%
76.4%		78%	78%	78%	84%	72%	70%	79%	78%	85%	76%	78%	77%	73%	78%	74%	78%	63%	73%		79%
56.3%		55%	60%	64%	55%	45%	54%	58%	51%	61%	48%	59%	59%	51%	66%	61%	68%	57%	43%		54%
88.1%		91%	91%	91%	92%	73%	80%	92%	87%	100%	93%	91%	91%	91%	76%	81%	100%	83%	91%	83%	86%
62.7%		61%	69%	71%	61%	61%	55%	52%	57%	69%	61%	49%	77%	61%	70%	69%	62%	57%	61%	61%	71%
69.9%		79%	79%	80%	58%	65%	74%	91%	73%	62%	74%	77%	62%	55%	74%	80%	54%	47%	62%	74%	78%
68.7%		71%	71%	66%	72%	58%	80%	78%	58%	70%	71%	72%	80%	72%	71%	78%	51%	49%	72%	61%	72%
70.4%		71%	71%	71%	73%	48%	65%	75%	81%	72%	73%	73%	72%	73%	78%	76%	71%	77%	73%	73%	42%
81.8%		83%	76%	83%	84%	74%	86%	77%	84%	83%	84%	72%	84%	73%	83%	91%	90%	84%	84%	77%	84%
69.0%		65%	77%	62%	71%	65%	62%	65%	71%	65%	65%	85%	71%	50%	77%	71%	77%	71%	71%	71%	68%
79.8%		77%	90%	77%	64%	65%	68%	100%	84%	84%	84%	52%	84%	74%	84%	91%	85%	81%	77%	84%	91%
71.4%		78%	80%	80%	79%	64%	71%	46%	61%	78%	71%	57%	57%	65%	78%	71%	71%	71%	71%	79%	100%
57.6%		58%	65%	65%	59%	54%	43%	65%	53%	53%	53%	49%	53%	53%	65%	65%	69%	83%	40%	58%	49%
61.4%		48%	70%	61%	57%	49%	73%	52%	67%	76%	59%	58%	70%	37%	80%	72%	60%	68%	37%	68%	66%
74.1%		69%	75%	76%	75%	72%	81%	85%	83%	84%	81%	58%	77%	75%	58%	81%	77%	82%	73%	58%	61%
55.6%		52%	54%	61%	59%	58%	58%	62%	58%	54%	58%	50%	58%	52%	55%	59%	54%	51%	51%	52%	57%
79.9%		80%	86%	83%	83%	72%	78%	77%	89%	89%	80%	64%	77%	83%	88%	86%	77%	72%	85%	77%	72%
70.6%	70%	78%	67%	67%	68%	73%	73%	78%	73%	84%	78%	55%	86%	70%	64%	73%	66%	60%	61%	84%	55%
78.2%		70%	86%	86%	84%	92%	84%	82%	77%	84%	73%	73%	82%	73%	72%	72%	83%	71%	73%	73%	73%
78.4%		88%	68%	68%	79%	82%	79%	89%	88%	84%	83%	73%	84%	84%	79%	68%	83%	81%	84%	68%	55%
61.7%		60%	64%	67%	67%	57%	67%	53%	61%	64%	62%	51%	64%	64%	72%	64%	52%	61%	67%		55%
80.6%		62%	92%	80%	77%	91%	78%	80%	73%	83%	78%	84%	100%	63%	84%	78%	85%	80%	65%	92%	87%
54.5%		65%	57%	57%	61%	39%	60%	55%	57%	51%	55%	29%	52%	36%	56%	58%	63%	62%	47%	65%	65%
67.3%		100%	80%	79%	65%	56%	69%	64%	69%	55%	64%	55%	55%	64%	72%	74%	64%	60%	72%	64%	65%
62.6%		70%	74%	67%	63%	43%	64%	70%	74%	58%	64%	58%	58%	58%	74%	69%	74%	27%	68%	57%	62%
82.3%		79%	79%	79%	85%	71%	92%	75%	100%	75%	75%	71%	88%	62%	92%	77%	75%	90%	100%	91%	91%
58.1%		59%	59%	50%	59%	59%	59%	74%	59%	53%	59%	59%	59%	59%	53%	53%	59%	59%	59%	59%	53%
60.0%		58%	52%	52%	71%	71%	58%	47%	36%	58%	52%	58%	71%	71%	58%	58%	58%	71%	71%	71%	58%
63.8%		62%	62%	73%	64%	62%	62%	72%	68%	66%	58%	58%	61%	49%	65%	69%	74%	65%	58%	62%	66%
62.5%	68%	76%	76%	76%	24%	56%	44%	68%	46%	49%	44%	68%	68%	68%	78%	72%	56%	79%	66%	63%	68%
59.7%	62%	62%	62%	62%	38%	61%	67%	62%	58%	65%	61%	62%	58%	68%	57%	55%	61%	64%	61%	61%	47%
61.3%		58%	56%	58%	64%	63%	60%	52%	66%	62%	66%	66%	66%	66%	57%	58%	60%	57%	66%	66%	60%
82.4%		90%	84%	84%	69%	81%	77%	77%	84%	81%	84%	81%	81%	81%	90%	90%	90%	84%	81%		77%
76.1%		70%	71%	71%	63%	64%	83%	71%	79%	89%	77%	55%	84%	67%	83%	84%	86%	79%	77%	86%	84%
84.1%		89%	78%	84%	59%	59%	71%	72%	71%	89%	100%	100%	100%	100%	89%	84%	78%	82%	100%	89%	89%
69.8%		64%	68%	74%	79%	49%	74%	71%	72%	77%	77%	51%	68%	55%	77%	85%	67%	79%	55%	80%	74%
53.8%		56%	53%	53%	51%	47%	66%	53%	51%	55%	56%	58%	51%	58%	56%	56%	53%	55%	46%	48%	54%
81.5%		80%	80%	78%	61%	69%	78%	69%	69%	78%	100%	100%	80%	93%	80%	78%	79%	86%	71%	100%	100%

Model Similarity Dendrogram

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