	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 4.1 Fast
Score	2nd 72.6%	10th 70.8%	3rd 72.6%	1st 73.5%	20th 65.7%	13th 69.8%	6th 71.5%	15th 69.3%	12th 69.8%	7th 71.4%	5th 71.9%	18th 68.6%	9th 70.9%	11th 69.9%	8th 70.9%	4th 72.4%	19th 68.3%	21st 64.1%	14th 69.7%	17th 68.7%	16th 69.2%
75.5%	73%	76%	85%	68%	72%	83%	89%	67%	81%	77%	81%	81%	71%	77%	77%	73%	72%	68%	71%	81%	63%
53.8%	55%	48%	63%	70%	7%	50%	55%	60%	48%	68%	55%	49%	48%	56%	59%	56%	50%	52%	55%	64%	62%
75.3%	79%	73%	69%	79%	69%	79%	73%	79%	69%	73%	79%	86%	79%	79%	73%	73%	71%	74%	73%	66%	86%
75.8%	75%	77%	75%	75%	73%	75%	73%	66%	82%	73%	78%	78%	75%	73%	83%	69%	77%	89%	70%	78%	78%
79.4%	84%	78%	89%	84%	80%	86%	84%	91%	80%	76%	78%	71%	76%	76%	84%	78%	69%	58%	91%	76%	79%
69.7%	67%	67%	58%	67%	69%	67%	76%	72%	80%	76%	72%	77%	72%	73%	63%	67%	80%	70%	72%	66%	52%
69.2%	67%	70%	73%	76%	67%	71%	64%	71%	64%	66%	65%	76%	63%	68%	77%	62%	68%	71%	66%	76%	73%
73.6%	80%	69%	71%	71%	73%	50%	81%	83%	81%	71%	77%	78%	69%	69%	85%	78%	77%	65%	64%	74%	80%
68.7%	65%	65%	64%	65%	62%	51%	70%	62%	70%	64%	80%	65%	73%	73%	64%	77%	72%	84%	64%	76%	76%
75.9%	78%	64%	84%	84%	78%	78%	75%	66%	78%	78%	78%	78%	78%	78%	64%	75%	73%	67%	78%	78%	84%
74.1%	83%	83%	77%	77%	83%	84%	76%	78%	70%	68%	76%	83%	64%	71%	62%	67%	85%	56%	75%	75%	63%
61.2%	78%	63%	65%	74%	69%	65%	54%	63%	59%	51%	65%	64%	51%	54%	58%	68%	54%	53%	65%	45%	67%
62.8%	66%	68%	68%	89%	64%	71%	61%	54%	57%	66%	68%	48%	62%	72%	58%	62%	54%	54%	68%	54%	54%
67.5%	73%	68%	73%	73%	66%	68%	73%	68%	76%	66%	70%	62%	65%	64%	68%	64%	64%	63%	71%	63%	60%
79.6%	75%	84%	75%	92%	73%	80%	75%	75%	75%	92%	91%	60%	74%	89%	88%	91%	79%	63%	76%	75%	89%
64.7%	60%	65%	65%	62%	46%	66%	71%	60%	70%	63%	71%	71%	70%	69%	67%	59%	55%	68%	71%	65%	65%
68.5%	72%	83%	86%	72%	64%	62%	63%	59%	69%	58%	79%	50%	65%	72%	74%	74%	70%	61%	68%	69%	69%
55.2%	60%	54%	51%	60%	65%	34%	46%	59%	53%	44%	53%	53%	51%	34%	69%	59%	73%	69%	58%	58%	57%
38.0%	41%	34%	38%	34%	64%	25%	41%	41%	38%	51%	36%	16%	41%	28%	56%	58%	26%	17%	14%	69%	30%
76.1%	73%	74%	74%	74%	76%	72%	76%	69%	70%	84%	76%	76%	77%	75%	78%	84%	80%	80%	77%	76%	77%
69.1%	67%	78%	78%	82%	61%	88%	70%	58%	70%	74%	58%	65%	73%	74%	58%	69%	63%	50%	88%	89%	39%
75.3%	76%	84%	84%	84%	61%	84%	73%	68%	70%	84%	79%	74%	70%	92%	79%	76%	69%	63%	79%		56%
74.4%	63%	72%	63%	67%	72%	90%	92%	77%	84%	84%	72%	74%	91%	84%	63%	80%	72%	64%	72%	67%	60%
53.8%	63%	65%	61%	68%	52%	60%	53%	42%	51%	60%	61%	34%	55%	51%	54%	65%	41%	41%	58%		41%
61.5%	61%	65%	65%	65%	63%	61%	65%	60%	65%	61%	68%	56%	61%	64%	54%	62%	65%	64%	64%	44%	59%
52.0%	57%	57%	51%	57%	57%	60%	51%	50%	48%	61%	63%	41%	58%	54%	41%	55%	40%	51%	56%	41%	44%
72.9%	78%	75%	75%	78%	73%	69%	70%	75%	68%	88%	67%	73%	91%	64%	67%	79%	69%	70%	78%	68%	55%
80.4%	84%	84%	84%	72%	51%	79%	86%	84%	77%	79%	90%	79%	84%	79%	74%	80%	87%	89%	88%	90%	69%
78.6%	100%	79%	88%	100%	100%	63%	80%	78%	76%	64%	69%	77%	73%	69%	80%	100%	69%	68%	80%	60%	78%
63.6%	78%	60%	78%	76%	81%	51%	62%	66%	56%	64%	60%	56%	52%	45%	69%	62%	60%	61%	56%	69%	74%
67.4%	65%	71%	65%	68%	49%	72%	64%	59%	64%	69%	69%	64%	65%	84%	75%	69%	64%	63%	74%	74%	69%
55.0%	50%	56%	59%	59%	59%	50%	56%	50%	59%	56%	50%	44%	50%	50%	56%	56%	58%	56%	56%	62%	62%
75.0%	79%	73%	69%	69%	69%	79%	69%	79%	69%	73%	79%	86%	79%	79%	79%	74%	71%	69%	73%	73%	86%
83.4%	84%	85%	100%	91%	49%	80%	83%	100%	84%	91%	76%	76%	91%	76%	84%	91%	91%	77%	76%	76%	90%
75.4%	72%	64%	80%	80%	47%	72%	77%	71%	77%	85%	77%	89%	85%	77%	91%	80%	100%	58%	56%	57%	89%
71.8%	64%	75%	77%	60%	43%	84%	70%	77%	73%	73%	73%	83%	77%	85%	57%	77%	55%	76%	79%	74%	76%
83.4%	86%	86%	85%	74%	86%	85%	86%	79%	86%	76%	86%	86%	86%	85%	86%	86%	82%	86%	82%	75%	82%
59.3%	71%	57%	62%	62%	72%	69%	77%	68%	57%	69%	55%	49%	64%	45%	62%	55%	51%	49%	55%	20%	77%
83.0%	85%	85%	91%	77%	64%	91%	85%	84%	84%	89%	91%	100%	100%	77%	85%	82%	70%	50%	84%	79%	91%
84.0%	88%	81%	78%	88%	78%	88%	81%	88%	78%	81%	88%	95%	88%	88%	88%	81%	80%	78%	81%	81%	88%
71.2%	77%	75%	77%	80%	55%	67%	80%	77%	72%	77%	77%	66%	77%	66%	80%	74%	71%	46%	61%	77%	64%
69.9%	74%	70%	61%	61%	67%	52%	74%	61%	67%	61%	80%	74%	67%	82%	74%	74%	67%	79%	74%	63%	86%
87.4%	95%	84%	86%	95%	95%	90%	95%	86%	97%	87%	75%	86%	86%	86%	86%	91%	95%	68%	81%	95%	76%

Model Similarity Dendrogram

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