	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	2nd 74.3%	17th 68.1%	10th 70.2%	1st 74.5%	15th 69.0%	18th 67.7%	5th 71.7%	9th 70.3%	7th 70.6%	8th 70.5%	13th 69.1%	20th 66.3%	6th 70.8%	19th 66.5%	4th 72.0%	3rd 72.9%	16th 68.3%	14th 69.1%	21st 65.4%	12th 69.9%	11th 70.2%
71.5%		71%	85%	77%	72%	85%	73%	74%	76%	76%	71%	66%	79%	59%	69%	76%	63%	58%	73%		55%
57.4%		55%	63%	68%	30%	70%	63%	49%	48%	62%	55%	66%	55%	61%	61%	63%	48%	65%	55%	55%	55%
78.7%		74%	63%	76%	91%	91%	74%	76%	69%	74%	91%	100%	100%	100%	74%	74%	74%	74%	32%	93%	74%
73.6%	71%	77%	75%	75%	63%	78%	71%	71%	76%	67%	78%	78%	78%	78%	76%	63%	77%	64%	78%	78%	73%
75.7%		77%	77%	89%	64%	64%	89%	81%	81%	89%	64%	64%	85%	64%	91%	89%	77%	64%	64%	64%	77%
73.4%		61%	58%	67%	65%	92%	76%	73%	72%	86%	80%	84%	84%	73%	58%	63%	84%	66%	80%	72%	73%
62.0%	65%	64%	54%	72%	67%	57%	54%	62%	64%	59%	57%	78%	47%	47%	75%	76%	76%	75%	46%	54%	53%
57.3%		50%	60%	60%	50%	50%	56%	70%	50%	66%	50%	50%	50%	44%	77%	83%	47%	55%	44%	50%	83%
65.1%		56%	55%	66%	62%	60%	64%	62%	60%	66%	64%	65%	65%	65%	70%	62%	72%	79%	56%	90%	63%
76.7%	78%	64%	75%	84%	78%	78%	77%	66%	78%	75%	78%	78%	78%	78%	77%	86%	73%	79%	78%	78%	75%
71.1%		77%	77%	84%	77%	66%	83%	78%	70%	64%	71%	76%	70%	64%	83%	76%	55%	52%	71%	64%	63%
61.2%	74%	65%	65%	74%	69%	57%	57%	65%	58%	42%	57%	64%	54%	58%	63%	72%	54%	41%	65%	58%	73%
73.6%	76%	77%	89%	89%	85%	72%	77%	72%	72%	69%	66%	66%	69%	66%	72%	74%	61%	69%	66%	79%	79%
66.9%	73%	68%	60%	54%	77%	60%	68%	68%	66%	68%	69%	52%	69%	77%	71%	69%	58%	66%	57%	77%	77%
86.6%		84%	89%	89%	91%	89%	89%	100%	91%	89%	89%	84%	84%	89%	80%	80%	84%	84%	89%	79%	78%
63.8%		62%	61%	63%	68%	61%	68%	61%	63%	63%	69%	60%	66%	57%	61%	61%	68%	69%	61%	68%	66%
61.6%		67%	72%	72%	63%	56%	65%	52%	58%	58%	63%	65%	59%	65%	69%	69%	50%	44%	68%	58%	58%
48.0%		38%	51%	51%	51%	35%	44%	52%	48%	46%	41%	20%	51%	31%	52%	51%	67%	81%	34%	56%	60%
39.9%	41%	34%	41%	41%	64%	28%	41%	36%	41%	45%	34%	16%	32%	16%	56%	52%	41%	58%	17%	52%	51%
72.8%	74%	59%	74%	74%	76%	74%	76%	74%	76%	74%	58%	76%	76%	74%	64%	76%	77%	81%	62%	76%	78%
87.7%	88%	92%	100%	100%	92%	92%	100%	92%	88%	88%	92%	92%	77%	78%	83%	85%	86%	75%	77%	92%	73%
88.4%	91%	91%	77%	86%	88%	100%	86%	88%	88%	86%	91%	92%	86%	92%	100%	91%	85%	83%	91%	80%	85%
72.9%	63%	72%	72%	72%	54%	84%	84%	83%	84%	89%	68%	60%	77%	73%	63%	63%	73%	78%	79%	68%	72%
68.4%		67%	73%	81%	66%	72%	67%	68%	67%	71%	66%	66%	76%	66%	73%	70%	66%	66%	66%	66%	55%
66.0%	61%	69%	60%	57%	76%	69%	69%	65%	74%	69%	61%	47%	69%	69%	68%	70%	72%	72%	69%	77%	43%
54.5%		68%	54%	54%	57%	48%	57%	49%	63%	57%	61%	60%	61%	49%	57%	60%	51%	33%	58%	51%	43%
71.5%		62%	77%	82%	65%	74%	77%	82%	82%	77%	62%	52%	76%	55%	79%	82%	59%	79%	83%	62%	63%
78.3%	79%	79%	79%	79%	72%	60%	79%	77%	90%	79%	90%	74%	79%	54%	76%	87%	79%	89%	74%	79%	91%
74.0%	86%	79%	88%	100%	67%	60%	80%	64%	77%	64%	60%	60%	60%	73%	80%	79%	62%	66%	80%	81%	88%
53.8%		52%	68%	78%	77%	34%	60%	55%	50%	45%	43%	43%	53%	23%	61%	68%	52%	51%	41%	49%	74%
79.4%	80%	81%	77%	84%	84%	92%	77%	72%	77%	77%	79%	72%	84%	84%	84%	79%	72%	78%	84%	72%	78%
34.3%		32%	36%	36%	36%	32%	36%	36%	39%	35%	35%	32%	32%	32%	35%	35%	35%	32%	32%	32%	35%
78.7%		74%	63%	76%	91%	91%	74%	76%	69%	74%	91%	100%	100%	100%	74%	74%	74%	74%	32%	91%	75%
79.0%	84%	69%	80%	86%	68%	77%	85%	78%	79%	91%	76%	76%	76%	77%	74%	74%	90%	77%	74%	76%	91%
76.2%	71%	62%	80%	80%	47%	75%	68%	71%	85%	68%	68%	89%	85%	92%	80%	74%	88%	81%	100%	64%	72%
74.9%	76%	83%	77%	77%	55%	67%	78%	76%	78%	77%	82%	68%	83%	67%	66%	84%	76%	74%	76%	78%
76.9%	78%	74%	76%	76%	73%	74%	74%	86%	76%	76%	74%	72%	78%	74%	78%	91%	72%	76%	74%	72%	91%
65.0%		62%	69%	64%	72%	64%	57%	59%	64%	64%	71%	64%	64%	64%	72%	68%	62%	72%	64%	64%	59%
84.0%	79%	79%	80%	91%	89%	70%	89%	100%	77%	90%	90%	77%	91%	70%	75%	87%	84%	91%	70%	86%	100%
87.8%		91%	91%	91%	91%	91%	91%	71%	78%	91%	91%	91%	91%	91%	85%	87%	95%	72%	91%	91%	85%
65.6%	73%	66%	66%	73%	64%	37%	66%	75%	71%	77%	71%	37%	71%	45%	80%	75%	63%	77%	54%	68%	68%
69.8%	74%	74%	61%	74%	61%	46%	74%	61%	67%	63%	80%	56%	61%	89%	80%	71%	74%	86%	74%	74%	66%
73.8%		69%	72%	81%	61%	80%	92%	95%	97%	84%	63%	63%	63%	77%	75%	67%	61%	64%	75%	61%	76%

Model Similarity Dendrogram

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