	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	7th 83.1%	10th 82.1%	1st 84.8%	5th 83.6%	14th 81.7%	20th 78.0%	4th 83.9%	15th 81.5%	9th 82.3%	3rd 84.5%	13th 81.8%	21st 77.4%	11th 82.0%	19th 78.4%	2nd 84.8%	6th 83.5%	12th 81.8%	17th 80.3%	16th 81.2%	8th 83.0%	18th 80.3%
84.8%		85%	89%	84%	87%	87%	88%	84%	85%	87%	88%	78%	84%	83%	88%	85%	83%	76%	87%	84%	84%
76.9%		78%	77%	79%	68%	88%	82%	71%	75%	74%	83%	88%	76%	94%	78%	63%	74%	76%	81%	79%	54%
70.3%		72%	61%	75%	72%	50%	94%	61%	57%	72%	72%	72%	72%	72%	72%	72%	71%	72%	72%	72%	72%
90.0%	92%	89%	91%	95%	85%	95%	91%	89%	89%	94%	94%	97%	93%	89%	90%	78%	86%	75%	94%	95%	89%
83.6%		80%	81%	84%	80%	80%	85%	90%	84%	95%	80%	80%	80%	80%	88%	96%	81%	80%	80%	80%	88%
83.6%		90%	92%	91%	92%	87%	83%	85%	86%	83%	82%	69%	80%	78%	85%	86%	81%	85%	83%	74%	80%
84.4%		88%	87%	87%	86%	77%	82%	92%	79%	88%	79%	76%	80%	78%	88%	86%	91%	86%	83%	83%	92%
75.1%		77%	78%	78%	74%	59%	73%	81%	70%	82%	71%	68%	75%	66%	83%	80%	83%	79%	69%	77%	79%
74.3%		51%	74%	71%	83%	67%	84%	79%	80%	78%	78%	53%	78%	70%	73%	79%	76%	79%	66%	87%	80%
93.0%	97%	97%	97%	96%	97%	97%	91%	77%	90%	97%	72%	97%	94%	97%	95%	96%	79%	97%	97%	97%	97%
84.3%		86%	90%	85%	84%	88%	87%	77%	84%	76%	89%	87%	83%	79%	85%	89%	74%	73%	90%	88%	92%
88.6%	91%	88%	93%	93%	92%	85%	93%	92%	90%	89%	86%	95%	87%	88%	85%	94%	77%	64%	97%	95%	87%
88.6%		93%	89%	89%	92%	87%	90%	93%	88%	87%	90%	92%	87%	90%	89%	88%	89%	77%	90%	91%	81%
89.5%		91%	92%	90%	86%	81%	95%	90%	93%	89%	94%	76%	89%	87%	94%	92%	91%	88%	93%	93%	85%
94.0%		93%	94%	94%	93%	95%	94%	96%	95%	95%	93%	95%	96%	90%	94%	94%	92%	95%	93%	95%	95%
90.6%		89%	91%	91%	89%	92%	94%	94%	93%	93%	87%	84%	89%	88%	91%	92%	90%	90%	95%	89%	91%
74.3%		86%	93%	79%	70%	70%	70%	50%	78%	79%	71%	72%	56%	65%	77%	81%	84%	84%	76%	94%	52%
87.4%		82%	90%	89%	86%	95%	86%	90%	91%	86%	88%	64%	80%	88%	90%	90%	89%	94%	89%	92%	88%
66.7%	59%	56%	70%	53%	79%	53%	64%	73%	67%	86%	58%	47%	69%	66%	85%	86%	69%	80%	48%	62%	70%
84.2%	81%	90%	92%	86%	84%	74%	90%	90%	92%	92%	81%	82%	86%	79%	92%	88%	80%	79%	80%	74%	76%
89.1%		84%	95%	94%	95%	84%	88%	88%	87%	95%	88%	87%	96%	89%	92%	88%	91%	88%	84%	80%	89%
87.6%		88%	86%	87%	87%	82%	86%	87%	89%	87%	84%	87%	89%	86%	90%	91%	88%	86%	90%	89%	92%
77.2%	80%	71%	81%	79%	90%	79%	82%	83%	77%	82%	82%	63%	82%	70%	72%	72%	72%	76%	81%	72%	76%
89.4%		82%	94%	94%	90%	91%	95%	82%	91%	92%	93%	90%	94%	90%	88%	88%	90%	81%	90%	91%	81%
91.4%		89%	89%	91%	89%	92%	88%	94%	95%	92%	92%	81%	95%	91%	95%	93%	88%	93%	95%	94%
77.4%		85%	76%	79%	78%	69%	77%	74%	76%	79%	80%	87%	75%	69%	82%	78%	71%	67%	87%	87%	72%
77.7%		73%	86%	79%	78%	83%	76%	79%	75%	77%	61%	70%	76%	83%	84%	76%	85%	84%	81%	64%	84%
79.0%		78%	80%	79%	86%	62%	79%	90%	87%	82%	78%	74%	78%	75%	87%	81%	79%	77%	72%	80%	76%
76.0%	84%	96%	83%	84%	80%	78%	78%	67%	76%	66%	80%	63%	76%	64%	75%	68%	78%	75%	69%		80%
86.6%		86%	94%	93%	88%	79%	88%	87%	93%	89%	84%	79%	87%	79%	86%	84%	81%	93%	86%	87%	89%
92.4%		92%	93%	94%	95%	89%	93%	90%	90%	96%	93%	89%	95%	89%	94%	95%	94%	90%	90%	94%
60.6%		59%	61%	60%	46%	46%	77%	71%	77%	59%	67%	77%	59%	46%	59%	59%	59%	46%	48%	77%	59%
65.8%		66%	67%	70%	67%	67%	94%	53%	52%	67%	67%	67%	67%	46%	66%	66%	66%	67%	67%	67%	66%
76.2%	81%	74%	76%	81%	71%	72%	76%	80%	80%	77%	75%	71%	74%	75%	81%	80%	78%	79%	69%	74%	77%
83.0%	93%	95%	91%	81%	57%	90%	74%	65%	73%	82%	73%	86%	85%	78%	96%	89%	87%	81%	96%		88%
89.2%		93%	92%	91%	94%	77%	95%	92%	89%	93%	93%	83%	96%	80%	88%	95%	89%	80%	84%	88%	92%
87.8%		85%	86%	87%	87%	86%	88%	86%	85%	87%	87%	89%	89%	88%	90%	91%	92%	88%	87%	89%	89%
84.0%		92%	86%	90%	78%	79%	91%	86%	86%	90%	91%	46%	90%	80%	95%	87%	76%	88%	80%	80%	89%
84.5%		87%	87%	87%	83%	76%	86%	95%	84%	92%	91%	80%	90%	81%	82%	85%	86%	83%	77%	80%	79%
79.4%		67%	98%	74%	77%	67%	67%	87%	84%	92%	83%	72%	67%	67%	92%	92%	89%	67%	77%	77%	92%
69.9%		61%	66%	70%	81%	54%	71%	87%	80%	70%	77%	50%	69%	60%	74%	73%	79%	79%	59%	73%	65%
72.7%	73%	75%	74%	74%	72%	64%	76%	73%	78%	81%	71%	75%	76%	80%	70%	63%	72%	71%	79%	66%	63%
80.7%		91%	85%	86%	67%	82%	68%	54%	70%	86%	91%	91%	89%	79%	86%	82%	88%	85%	80%	91%	62%

Model Similarity Dendrogram

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