	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	1st 86.0%	7th 83.8%	4th 85.0%	2nd 85.9%	11th 82.7%	19th 80.4%	15th 81.9%	14th 82.3%	9th 83.6%	5th 84.1%	12th 82.6%	21st 79.2%	10th 83.4%	18th 81.3%	8th 83.7%	3rd 85.3%	16th 81.9%	20th 79.7%	13th 82.4%	6th 84.0%	17th 81.6%
81.2%		82%	86%	83%	81%	82%	82%	80%	82%	81%	84%	80%	82%	77%	81%	82%	83%	69%	86%		80%
72.4%		84%	68%	75%	60%	85%	83%	75%	67%	66%	74%	63%	68%	83%	71%	66%	70%	67%	80%	83%	60%
78.5%		79%	68%	72%	79%	79%	92%	62%	72%	79%	79%	98%	79%	79%	79%	79%	79%	79%	79%	79%	79%
90.8%		85%	94%	93%	90%	88%	93%	91%	93%	94%	95%	93%	95%	87%	88%	90%	85%	89%	88%	93%	91%
84.5%		82%	81%	82%	82%	82%	86%	90%	83%	92%	82%	82%	82%	82%	88%	90%	84%	82%	82%		92%
84.5%		94%	93%	94%	88%	86%	84%	90%	83%	82%	85%	85%	79%	81%	83%	90%	80%	84%	77%	74%	77%
87.4%		86%	90%	94%	83%	79%	87%	99%	86%	84%	81%	81%	84%	85%	94%	96%	94%	86%	78%	85%	96%
78.5%		78%	73%	83%	74%	71%	74%	93%	75%	87%	81%	79%	79%	76%	83%	84%	77%	72%	73%	77%	80%
76.5%		56%	72%	77%	79%	58%	69%	81%	68%	84%	75%	56%	88%	76%	87%	89%	82%	87%	73%	86%	87%
89.8%	93%	93%	92%	95%	93%	93%	76%	76%	90%	89%	90%	93%	93%	93%	88%	89%	86%	81%	93%	93%	96%
80.5%		88%	89%	89%	82%	86%	88%	88%	80%	76%	86%	91%	78%	80%	86%	84%	66%	56%	81%	82%	53%
84.4%	91%	92%	88%	93%	92%	80%	82%	91%	85%	83%	81%	92%	85%	77%	78%	84%	73%	74%	92%	81%	78%
91.8%		95%	94%	94%	96%	91%	93%	93%	90%	93%	92%	86%	93%	92%	93%	92%	91%	94%	92%	92%	79%
91.1%		91%	91%	97%	92%	93%	83%	90%	87%	96%	96%	81%	95%	95%	89%	87%	88%	96%	92%	90%	93%
92.2%		95%	95%	95%	95%	90%	95%	94%	94%	96%	96%	88%	95%	90%	88%	88%	87%	90%	90%	88%	94%
92.0%		82%	98%	95%	98%	95%	97%	96%	99%	85%	87%	93%	94%	96%	95%	89%	92%	87%	97%	87%	78%
74.2%		88%	88%	75%	71%	82%	68%	54%	76%	83%	79%	68%	61%	68%	84%	81%	72%	63%	87%	84%	52%
83.7%		78%	83%	81%	85%	89%	79%	86%	90%	80%	84%	83%	83%	86%	81%	79%	86%	91%	80%	92%	77%
75.6%		68%	86%	70%	76%	64%	83%	68%	82%	87%	68%	60%	75%	79%	91%	91%	81%	58%	61%	88%	75%
87.9%		97%	87%	97%	92%	85%	95%	87%	92%	94%	74%	82%	94%	91%	89%	78%	87%	83%	91%	89%	75%
88.1%		81%	93%	92%	93%	82%	86%	83%	85%	96%	85%	85%	94%	81%	96%	94%		91%	81%	82%	94%
91.2%		94%	88%	90%	92%	92%	91%	95%	95%	89%	92%	85%	94%	93%	95%	87%	96%	84%	94%	92%	85%
81.7%		76%	88%	78%	71%	84%	90%	87%	86%	88%	89%	67%	85%	75%	82%	90%	81%	77%	87%	77%	76%
89.4%		81%	86%	93%	92%	86%	88%	90%	89%	93%	89%	92%	89%	92%	89%	92%	88%	85%	91%	92%	90%
90.6%		93%	89%	92%	94%	94%	92%	93%	96%	94%	93%	74%	90%	89%	92%	92%	91%	90%	89%	95%	81%
74.9%		85%	75%	82%	69%	65%	76%	71%	70%	74%	79%	77%	72%	67%	84%	83%	62%	66%	82%	77%	81%
82.1%		75%	90%	89%	76%	82%	83%	88%	91%	81%	67%	69%	84%	87%	87%	82%	86%	70%	84%	83%	88%
81.2%		83%	87%	86%	91%	71%	82%	85%	91%	84%	86%	58%	79%	72%	91%	83%	81%	86%	74%	77%	77%
75.3%		95%	87%	87%	84%	70%	78%	71%	75%	69%	67%	67%	68%	62%	86%	85%	67%	73%	71%	67%	77%
78.8%		78%	81%	81%	91%	81%	78%	88%	77%	79%	76%	75%	79%	75%	79%	72%	77%	75%	79%	77%	79%
87.4%		88%	87%	87%	88%	85%	86%	88%	88%	87%	86%	90%	88%	88%	88%	88%	85%	87%	88%	88%	88%
66.0%		63%	66%	66%	78%	51%	63%	66%	83%	63%	58%	56%	58%	58%	63%	63%	69%	78%	78%	78%	63%
65.3%		69%	60%	61%	71%	71%	10%	61%	60%	69%	71%	71%	71%	71%	69%	69%	69%	71%	71%	71%	69%
87.4%	90%	85%	91%	94%	78%	83%	85%	92%	88%	85%	86%	83%	89%	86%	96%	91%	91%	89%	80%	85%	89%
71.1%	77%	75%	76%	93%	46%	76%	58%	51%	55%	54%	58%	86%	67%	68%	71%	87%	85%	72%	81%	72%	85%
84.4%		88%	94%	88%	78%	71%	83%	93%	88%	91%	90%	81%	90%	75%	90%	86%	74%	79%	75%	86%	87%
91.8%		95%	95%	95%	93%	90%	95%	80%	98%	87%	94%	88%	96%	88%	91%	95%	90%	85%	92%	94%	94%
88.8%		96%	92%	88%	83%	96%	89%	86%	96%	90%	88%	82%	90%	82%	97%	86%	95%	86%	82%	84%	89%
82.6%		92%	92%	93%	86%	88%	96%	89%	91%	86%	91%	73%	87%	86%	0%	90%	76%	77%	81%	87%	91%
84.0%		79%	98%	82%	78%	71%	94%	82%	82%	94%	78%	77%	79%	79%	94%	94%	90%	79%	79%	78%	94%
79.6%		72%	76%	86%	94%	59%	76%	82%	88%	79%	92%	60%	88%	79%	80%	81%	83%	76%	67%	92%	81%
76.5%	79%	74%	77%	80%	82%	65%	85%	77%	76%	83%	77%	84%	75%	86%	71%	76%	73%	67%	77%	75%	68%
83.5%		93%	70%	75%	62%	85%	70%	59%	71%	89%	90%	90%	91%	85%	92%	92%	88%	95%	90%	94%	90%

Model Similarity Dendrogram

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