	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 76.0%	3rd 75.1%	4th 74.4%	1st 76.6%	7th 74.1%	20th 68.9%	11th 73.0%	9th 73.9%	16th 69.8%	6th 74.1%	10th 73.6%	21st 68.9%	12th 72.6%	13th 72.1%	8th 74.0%	4th 74.4%	17th 69.6%	19th 69.0%	15th 70.4%	18th 69.1%	14th 71.6%
72.0%	70%	76%	72%	73%	73%	55%	78%	82%	69%	76%	74%	75%	71%	66%	77%	76%	62%	66%	70%	75%	77%
72.7%	71%	74%	74%	72%	68%	70%	71%	70%	72%	74%	76%	73%	77%	76%	75%	76%	76%	60%	76%	70%	76%
67.1%	61%	67%	70%	72%	73%	72%	68%	71%	61%	73%	67%	74%	65%	68%	67%	69%	65%	63%	59%	58%	67%
56.4%	61%	61%	46%	61%	61%	63%	64%	55%	56%	49%	71%	56%	68%	71%	51%	51%	45%	39%	77%	37%	41%
89.8%	91%	89%	98%	96%	84%	88%	91%	96%	98%	84%	89%	86%	86%	87%	93%	88%	87%	89%	89%	83%	93%
79.0%	82%	83%	92%	93%	88%	64%	84%	85%	77%	83%	71%	81%	71%	69%	84%	84%	77%	81%	67%	59%	85%
87.6%	89%	82%	94%	88%	93%	82%	88%	89%	89%	96%	90%	90%	89%	79%	95%	91%	87%	74%	77%	92%	86%
74.5%	76%	75%	64%	73%	75%	56%	74%	69%	74%	89%	74%	80%	79%	75%	88%	78%	76%	82%	71%	67%	69%
82.8%	89%	88%	76%	92%	78%	78%	74%	86%	82%	86%	91%	88%	83%	85%	88%	84%	83%	72%	78%	74%	83%
64.9%	75%	66%	48%	74%	66%	70%	75%	64%	59%	61%	75%	57%	70%	74%	53%	63%	58%	73%	79%	63%	39%
80.0%	84%	80%	93%	93%	76%	95%	87%	90%	76%	78%	74%	71%	72%	68%	93%	81%	67%	51%	79%	81%	90%
55.8%	71%	68%	48%	61%	60%	45%	67%	60%	53%	58%	60%	46%	60%	63%	44%	62%	53%	44%	63%	49%	37%
72.2%	67%	74%	82%	76%	74%	85%	70%	78%	64%	70%	79%	50%	72%	70%	77%	70%	75%	62%	79%	70%	73%
67.0%	68%	71%	72%	70%	60%	73%	71%	67%	63%	58%	67%	61%	71%	70%	71%	74%	67%	57%	63%	69%	64%
69.7%	79%	74%	75%	80%	77%	77%	71%	78%	67%	75%	68%	55%	70%	70%	0%	78%	72%	71%	72%	79%	76%
74.4%	78%	77%	77%	80%	83%	58%	78%	80%	73%	77%	76%	76%	75%	76%	79%	76%	62%	67%	63%	74%	77%
57.0%	62%	62%	64%	63%	66%	47%	46%	47%	46%	56%	47%	59%	59%	51%	73%	65%	62%	46%	61%	54%	61%
60.0%	66%	63%	66%	68%	61%	39%	58%	62%	58%	66%	65%	61%	61%	57%	66%	62%	52%	58%	60%	52%	58%
68.1%	64%	63%	66%	71%	71%	47%	76%	60%	68%	82%	58%	64%	64%	64%	85%	85%	32%	92%	57%	73%	88%
76.8%	78%	82%	80%	81%	67%	80%	80%	75%	70%	72%	78%	73%	78%	76%	80%	77%	80%	72%	79%	78%	77%
78.6%	88%	77%	74%	87%	80%	66%	81%	82%	80%	82%	86%	78%	79%	77%	80%	79%	77%	77%	72%	74%	75%
72.8%	75%	79%	75%	73%	76%	74%	75%	75%	70%	76%	72%	64%	71%	75%	78%	77%	74%	67%	77%	74%	52%
73.6%	80%	75%	71%	73%	71%	74%	73%	79%	73%	78%	77%	57%	75%	70%	78%	74%	75%	75%	67%		77%
81.1%	88%	86%	83%	83%	83%	82%	83%	87%	84%	82%	81%	70%	81%	81%	81%	82%	77%	76%	76%	77%	80%
66.8%	65%	73%	73%	68%	63%	72%	70%	62%	61%	57%	70%	62%	63%	76%	60%	54%	70%	74%	65%	76%	69%
73.8%	83%	73%	70%	73%	75%	68%	72%	65%	70%	74%	76%	72%	72%	83%	68%	73%	83%	63%	75%	79%	82%
68.0%	73%	67%	75%	77%	68%	48%	69%	69%	69%	74%	57%	75%	71%	58%	75%	76%	52%	73%	61%	71%	69%
75.9%	76%	79%	74%	82%	85%	61%	79%	86%	84%	91%	78%	76%	81%	65%	91%	83%	59%	73%	65%	63%	62%
60.0%	68%	71%	61%	70%	62%	45%	71%	74%	41%	51%	68%	36%	56%	68%	60%	60%	56%	74%	70%	61%	38%
59.1%	58%	56%	58%	64%	81%	55%	49%	47%	51%	55%	63%	63%	55%	58%	61%	60%	69%	69%	54%	55%	61%
58.8%	66%	62%	66%	59%	59%	61%	50%	48%	46%	61%	53%	45%	54%	58%	65%	59%	64%	62%	61%	67%	69%
67.4%	73%	67%	64%	63%	61%	62%	67%	63%	73%	61%	67%	60%	69%	67%	67%	65%	70%	71%	75%	77%	74%
76.0%	70%	76%	79%	81%	82%	82%	77%	80%	70%	82%	76%	83%	74%	77%	78%	77%	73%	72%	68%	66%	73%
75.2%	80%	76%	81%	75%	79%	74%	74%	82%	77%	79%	73%	69%	75%	73%	81%	79%	77%	73%	65%	65%	73%
76.9%	84%	80%	80%	80%	71%	67%	61%	77%	75%	80%	80%	80%	80%	75%	76%	78%	79%	80%	78%	84%	69%
74.5%	74%	82%	82%	69%	68%	83%	72%	76%	64%	70%	70%	79%	70%	76%	65%	65%	82%	80%	77%	75%	86%
77.6%	88%	85%	88%	89%	79%	85%	70%	70%	75%	77%	76%	59%	76%	75%	85%	76%	76%	76%	70%	75%	80%
87.2%	91%	93%	92%	93%	89%	94%	88%	90%	88%	89%	88%	73%	94%	81%	93%	92%	83%	86%	82%	61%	91%
70.8%	80%	71%	72%	77%	75%	67%	75%	74%	72%	77%	67%	70%	73%	67%	76%	76%	64%	59%	65%	61%	68%
87.0%	81%	87%	90%	92%	93%	93%	88%	91%	81%	93%	87%	94%	85%	88%	91%	88%	85%	83%	79%	77%	81%
81.8%	92%	84%	93%	87%	84%	75%	79%	88%	82%	85%	92%	83%	83%	79%	90%	83%	79%	36%	71%	85%	88%
73.6%	77%	80%	67%	67%	72%	67%	76%	80%	69%	81%	82%	73%	75%	83%	72%	79%	61%	78%	69%	61%	77%
71.3%	75%	76%	75%	75%	77%	65%	67%	70%	71%	70%	76%	67%	67%	77%	73%	75%	71%	72%	67%	63%	68%

Model Similarity Dendrogram

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