	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	1st 65.8%	7th 62.9%	4th 63.5%	5th 63.3%	13th 59.8%	12th 60.1%	10th 61.6%	16th 57.9%	18th 56.5%	2nd 65.0%	6th 63.2%	21st 50.7%	3rd 63.9%	11th 60.1%	8th 62.8%	9th 62.5%	17th 57.3%	20th 56.0%	14th 59.7%	19th 56.4%	15th 58.3%
64.3%	67%					59%															67%
51.8%	48%									57%	56%	54%	56%	56%	57%	48%					34%
48.4%	51%										59%		44%					44%			44%
66.7%	63%	69%	61%	68%	61%	71%	67%	72%	62%	66%	68%	68%	73%	68%	66%	61%	66%	70%	70%	67%	63%
75.0%	75%																				75%
61.5%	67%																				56%
63.0%	63%	59%	71%	67%	67%	65%	67%	57%	51%	75%	57%	58%	75%	61%	77%	64%	61%	50%	63%	63%	51%
46.5%	54%																				39%
74.0%	75%																				73%
62.3%	62%	62%	60%	55%	64%	66%	67%	58%	60%	65%	75%	58%	73%	62%	64%	75%	63%	44%	55%		58%
67.5%	58%																				77%
61.9%	58%	69%	65%	71%	68%	65%	59%	73%	65%	73%	57%	55%	58%	65%	58%	58%	46%	51%	67%	49%	69%
66.3%	77%	71%	77%	74%	70%	71%	67%	50%	63%	74%	70%	47%	64%	66%	65%	69%	69%	50%	66%	67%
56.1%	63%	59%	63%	60%	56%	58%	59%	51%	47%	61%	63%	63%	61%	57%	60%	54%	55%	51%	63%	40%	35%
59.5%	69%	66%	57%	58%	67%	66%	50%	36%	41%	74%	64%	40%	58%	50%	73%	66%	57%	65%	70%	53%	70%
65.7%	61%													62%							74%
74.6%	74%					66%				86%	80%		74%	70%				57%			90%
63.0%	62%										55%		74%	49%							75%
45.7%	47%	34%	57%	54%	51%	39%	40%	39%	54%	57%	39%	34%	56%	53%	54%	59%	44%	32%	32%	45%	39%
53.2%	50%	50%	49%	50%	54%	56%	54%	55%	54%	52%	54%	58%	55%	54%	49%	53%	58%	53%	49%	58%	52%
51.0%	57%	57%	55%	58%	44%	43%	51%	50%	52%	52%	55%	50%	55%	52%	52%	51%	48%	44%	43%	52%
64.3%	64%	67%	67%	71%	66%	70%	62%	50%	51%	77%	74%	47%	67%	66%	68%	63%	69%	54%	69%	64%
51.1%	50%	43%	46%	49%	61%	75%	60%	58%	55%	43%	56%	35%	58%	65%	47%	50%	39%	35%	49%	44%	55%
61.7%	74%	71%	74%	73%	74%	63%	65%	53%	61%	74%	71%	20%	65%	59%	71%	66%	68%	67%	59%	46%	21%
57.3%	64%	63%	64%	57%	58%	67%	64%	55%	46%	66%	58%	16%	68%	62%	62%	63%	51%	62%	62%	38%
60.3%	66%									60%											55%
61.7%	71%		73%			42%		70%			47%		75%					49%			67%
68.7%	75%	73%	75%	75%	64%	53%	71%	83%	62%	70%	69%	70%	80%	59%	83%	74%	53%	64%	58%	62%
50.8%	59%	76%	64%	60%	55%	40%	59%	49%	49%	45%	59%	38%	40%	40%	45%	53%	44%	41%	64%	45%	42%
68.5%	78%																				59%
60.2%	66%	69%	62%	71%	66%	66%	51%	40%	47%	60%	66%	45%	64%	61%	60%	64%	61%	53%	69%	64%
90.0%	87%										78%		95%					95%			95%
46.3%	51%												44%								44%
61.2%	65%	69%	69%	54%	38%	72%	69%	64%	58%	59%	66%	64%	70%	64%	62%	62%	66%	56%	67%	61%	31%
60.4%	67%	55%	59%	58%	37%	65%	65%	65%	65%	63%	56%	55%	65%	65%	58%	62%	55%	57%	63%	68%	65%
68.4%	77%	75%	77%	76%	62%	59%	71%	68%	68%	77%	71%	64%	67%	64%	71%	74%	59%	72%	59%	56%
83.0%	86%																				80%
61.5%	92%																				31%
56.9%	73%	52%	56%	60%	59%	46%	67%	60%	54%	56%	51%	57%	59%	51%	61%	65%	62%	57%	42%	50%
69.2%	71%					75%					80%		63%					63%			63%
73.9%	75%	69%	71%	74%	75%	56%	77%	76%	84%	86%	80%	60%	70%	67%	80%	84%	64%	69%	71%	90%
59.0%	58%	68%	51%	63%	58%	42%	55%	57%	51%	56%	69%	61%	58%	66%	64%	61%	59%	62%	63%	59%	58%
64.0%	58%					66%				70%	56%		60%	70%				57%			75%

Model Similarity Dendrogram

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