	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	1st 82.9%	2nd 82.6%	17th 76.1%	14th 76.3%	9th 79.3%	20th 73.2%	11th 78.8%	5th 81.1%	10th 78.8%	6th 80.9%	7th 79.6%	13th 76.7%	8th 79.3%	15th 76.3%	4th 81.3%	3rd 82.3%	16th 76.2%	21st 73.0%	12th 77.5%	18th 75.8%	19th 74.9%
82.1%		88%	85%	91%	76%	64%	79%	89%	80%	80%	79%	91%	85%	77%	78%	86%	88%	83%	85%	85%	74%
76.9%		70%	77%	82%	48%	88%	66%	71%	63%	80%	94%	92%	84%	82%	81%	76%	74%	74%	90%	77%	68%
64.6%		70%	0%	0%	64%	73%	68%	85%	64%	79%	76%	76%	73%	74%	75%	72%	68%	68%	65%	68%	74%
88.4%	93%	82%	92%	88%	91%	83%	91%	95%	96%	90%	91%	87%	92%	82%	90%	93%	85%	77%	88%	86%	85%
88.0%		90%	85%	92%	88%	85%	87%	90%	96%	96%	94%	93%	87%	90%	88%	91%	90%	73%	87%	88%	69%
78.1%		83%	79%	83%	85%	81%	78%	88%	85%	82%	83%	65%	77%	70%	72%	78%	82%	74%	78%	65%	74%
90.4%	93%	91%	89%	92%	82%	92%	86%	94%	93%	93%	85%	89%	91%	92%	93%	87%	95%	88%	82%	95%	96%
76.0%		77%	74%	89%	80%	47%	77%	85%	78%	80%	72%	80%	80%	67%	89%	86%	73%	73%	64%	80%	69%
81.5%		86%	86%	80%	81%	66%	76%	85%	77%	93%	84%	84%	79%	81%	77%	93%	92%	83%	79%	75%	74%
84.3%	88%	87%	87%	93%	87%	96%	81%	81%	87%	85%	82%	87%	86%	87%	87%	82%	66%	64%	87%	87%	83%
81.1%		91%	90%	92%	84%	83%	89%	89%	79%	80%	89%	80%	65%	76%	77%	79%	64%	62%	82%	83%	88%
85.8%	93%	89%	90%	97%	96%	74%	85%	87%	91%	73%	85%	96%	65%	86%	93%	87%	72%	82%	90%	80%	90%
79.5%	68%	86%	84%	88%	85%	82%	81%	77%	79%	81%	90%	91%	81%	89%	77%	87%	68%	54%	83%	70%	68%
80.6%	85%	83%	84%	82%	87%	73%	84%	84%	83%	83%	82%	64%	82%	66%	85%	81%	78%	86%	90%	75%	76%
88.1%		91%	94%	86%	90%	86%	91%	90%	90%	90%	95%	84%	92%	88%	93%	90%	77%	79%	85%	88%	82%
76.4%		84%	88%	83%	84%	63%	76%	80%	74%	79%	70%	76%	80%	75%	74%	84%	81%	72%	78%	63%	64%
61.1%		69%	72%	72%	61%	54%	65%	54%	62%	61%	56%	46%	52%	53%	75%	78%	45%	56%	69%	58%	63%
65.8%		66%	78%	82%	76%	46%	60%	72%	53%	65%	53%	69%	66%	55%	75%	71%	73%	61%	73%	61%	62%
61.3%	64%	52%	66%	56%	74%	46%	59%	70%	65%	73%	60%	47%	67%	56%	76%	76%	66%	45%	44%	66%	60%
82.6%	84%	87%	88%	87%	90%	77%	86%	83%	76%	91%	77%	78%	89%	75%	89%	87%	79%	77%	77%	76%	81%
86.3%	85%	93%	93%	83%	96%	78%	94%	89%	96%	88%	92%	92%	96%	79%	77%	84%	88%	80%	66%	95%	69%
84.1%	83%	88%	91%	86%	90%	65%	85%	94%	90%	86%	79%	91%	89%	84%	91%	91%	80%	79%	70%	77%	77%
76.9%	71%	81%	75%	75%	88%	85%	82%	78%	71%	80%	80%	72%	76%	82%	68%	70%	77%	73%	81%	78%	72%
86.6%		92%	96%	93%	87%	92%	84%	89%	88%	91%	98%	77%	88%	91%	86%	92%	78%	68%	84%	79%	79%
78.6%	83%	83%	83%	80%	83%	76%	83%	81%	83%	81%	87%	66%	81%	68%	74%	78%	79%	71%	83%	73%	74%
71.5%		74%	75%	71%	76%	67%	70%	69%	75%	71%	77%	72%	71%	84%	68%	73%	72%	67%	78%	69%	51%
76.5%		82%	87%	85%	79%	59%	71%	82%	79%	82%	65%	79%	76%	72%	80%	86%	76%	81%	77%	65%	66%
77.9%	91%	84%	76%	88%	78%	53%	84%	90%	87%	79%	75%	69%	75%	63%	87%	81%	81%	77%	68%	75%	74%
72.2%	86%	89%	90%	89%	82%	60%	75%	70%	67%	61%	59%	58%	63%	62%	82%	80%	63%	72%	64%	65%	79%
77.7%		83%	82%	92%	78%	75%	62%	84%	78%	77%	72%	65%	74%	74%	83%	88%	66%	83%	82%	78%	78%
84.8%	79%	89%	93%	83%	85%	87%	85%	86%	85%	90%	86%	84%	89%	90%	85%	89%	88%	78%	81%	70%	79%
69.3%		78%	0%	0%	85%	75%	85%	63%	85%	70%	72%	72%	75%	74%	77%	74%	81%	81%	83%	81%	76%
58.0%		64%	0%	0%	57%	66%	57%	78%	57%	72%	69%	69%	66%	67%	65%	64%	61%	61%	59%	61%	67%
80.2%	86%	78%	86%	89%	74%	75%	77%	82%	83%	80%	78%	72%	78%	75%	83%	87%	86%	84%	76%	76%	79%
65.0%	76%	80%	70%	71%	69%	67%	57%	53%	53%	59%	55%	69%	60%	67%	70%	62%	62%	54%	83%	70%	59%
77.6%	83%	84%	88%	86%	44%	72%	83%	86%	78%	84%	82%	72%	81%	74%	80%	82%	78%	64%	67%	81%	80%
87.2%		91%	94%	85%	94%	84%	91%	79%	93%	85%	95%	74%	94%	88%	87%	87%	92%	81%	85%	87%	78%
88.3%		90%	94%	92%	88%	90%	91%	94%	88%	96%	97%	76%	98%	85%	87%	96%	80%	71%	90%	79%	84%
77.8%	87%	81%	85%	85%	81%	66%	85%	83%	79%	86%	73%	78%	81%	61%	88%	80%	77%	59%	61%	77%	80%
80.2%		87%	0%	0%	80%	91%	85%	97%	81%	96%	93%	93%	91%	91%	90%	87%	85%	98%	82%	85%	91%
82.0%		89%	82%	82%	75%	68%	87%	86%	83%	88%	82%	74%	80%	79%	89%	87%	76%	80%	88%	78%	88%
75.8%	80%	82%	74%	77%	72%	63%	77%	77%	76%	80%	76%	77%	83%	79%	80%	81%	74%	66%	75%	70%	72%
70.7%		89%	71%	76%	59%	74%	72%	48%	62%	64%	84%	74%	73%	73%	73%	74%	61%	81%	73%	64%	69%

Model Similarity Dendrogram

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