	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 88.4%	9th 84.0%	4th 85.9%	2nd 86.2%	7th 84.1%	21st 79.4%	11th 84.0%	8th 84.0%	6th 84.8%	10th 84.0%	12th 83.9%	19th 81.4%	14th 83.4%	18th 81.7%	3rd 86.0%	5th 85.8%	15th 82.8%	20th 80.3%	17th 81.9%	13th 83.5%	16th 82.4%
85.8%		86%	90%	86%	92%	85%	87%	86%	95%	86%	88%	84%	88%	82%	90%	83%	77%	79%	86%	88%	79%
79.1%		83%	85%	86%	80%	93%	84%	76%	76%	77%	78%	76%	78%	89%	85%	76%	75%	69%	72%	74%	70%
66.3%		72%	61%	67%	68%	52%	72%	64%	52%	72%	68%	68%	72%	68%	72%	72%	66%	68%	52%	68%	72%
92.4%	96%	86%	97%	95%	96%	90%	96%	94%	94%	95%	94%	93%	94%	88%	91%	86%	89%	83%	93%	95%	96%
87.3%		84%	86%	90%	84%	84%	89%	90%	86%	91%	84%	84%	84%	84%	92%	94%	91%	85%	84%	87%	92%
88.6%		88%	88%	88%	96%	96%	93%	96%	91%	83%	85%	92%	85%	91%	81%	89%	88%	86%	83%	86%	86%
84.8%	88%	85%	86%	87%	88%	78%	84%	93%	87%	84%	79%	78%	82%	80%	89%	89%	84%	85%	80%	88%	86%
80.2%		86%	82%	83%	79%	75%	78%	80%	80%	87%	89%	79%	80%	66%	88%	89%	74%	71%	77%	79%	83%
75.1%		66%	71%	72%	68%	60%	70%	78%	78%	82%	72%	74%	81%	77%	77%	77%	85%	82%	69%	81%	82%
90.0%	93%	93%	92%	92%	93%	96%	83%	90%	88%	91%	75%	95%	96%	93%	93%	93%	82%	68%	93%	96%	95%
78.6%		87%	88%	90%	78%	85%	76%	89%	77%	76%	87%	77%	73%	72%	73%	78%	65%	54%	83%	85%	80%
88.0%	92%	93%	95%	92%	94%	91%	84%	92%	94%	75%	84%	94%	88%	88%	89%	85%	88%	63%	92%	89%	87%
91.2%		95%	97%	96%	94%	78%	92%	94%	91%	90%	94%	93%	90%	94%	92%	90%	92%	93%	94%	94%	71%
89.2%	91%	89%	91%	91%	92%	92%	91%	92%	89%	90%	93%	78%	86%	85%	91%	91%	89%	85%	89%	92%	87%
92.9%		94%	93%	94%	93%	95%	95%	97%	94%	96%	93%	94%	94%	94%	94%	93%	89%	76%	94%		94%
91.0%		83%	94%	93%	92%	88%	92%	92%	96%	90%	91%	94%	92%	95%	89%	90%	91%	83%	95%	88%	93%
73.7%		82%	77%	80%	75%	78%	75%	49%	73%	79%	84%	76%	69%	67%	85%	80%	85%	68%	76%	64%	51%
81.2%		77%	80%	82%	88%	82%	79%	82%	83%	78%	78%	80%	79%	82%	82%	77%	86%	92%	75%	82%	80%
70.4%	67%	57%	77%	64%	74%	45%	68%	67%	73%	79%	73%	49%	75%	77%	81%	86%	82%	93%	50%	75%	67%
88.8%	92%	89%	90%	96%	94%	83%	97%	98%	97%	97%	71%	91%	92%	86%	88%	89%	88%	82%	94%	79%	71%
87.2%		83%	87%	90%	86%	88%	85%	83%	85%	90%	88%	85%	93%	88%	90%	93%	83%	86%	85%	83%	93%
89.2%		89%	83%	88%	86%	89%	85%	89%	94%	87%	92%	85%	91%	90%	95%	96%	82%	87%	96%	91%	90%
84.4%	94%	82%	82%	82%	82%	77%	95%	87%	89%	95%	90%	74%	84%	84%	80%	83%	81%	80%	88%	81%	83%
91.5%	96%	89%	84%	89%	94%	96%	97%	91%	90%	92%	94%	94%	96%	94%	91%	89%	93%	92%	94%	94%	72%
89.5%		87%	87%	90%	92%	91%	86%	92%	92%	89%	93%	82%	93%	92%	93%	94%	82%	86%	93%	85%	91%
77.2%		85%	87%	83%	73%	70%	79%	72%	73%	75%	85%	79%	72%	70%	82%	78%	68%	71%	87%	77%
85.3%		76%	91%	91%	91%	87%	88%	93%	92%	81%	69%	73%	77%	87%	93%	80%	92%	89%	83%	85%	87%
82.7%		85%	85%	85%	90%	69%	87%	91%	87%	87%	85%	62%	81%	70%	91%	97%	78%	90%	70%	82%
78.1%	78%	83%	83%	85%	81%	72%	82%	76%	76%	77%	74%	74%	75%	73%	82%	82%	77%	76%	78%		78%
84.2%		86%	88%	93%	81%	76%	89%	88%	85%	84%	82%	81%	84%	81%	87%	78%	87%	84%	83%	86%	81%
91.5%		92%	93%	93%	91%	86%	90%	89%	93%	88%	93%	92%	93%	92%	93%	93%	93%	93%	92%	87%	93%
70.6%		63%	67%	70%	83%	52%	63%	79%	83%	63%	83%	83%	63%	52%	63%	63%	63%	83%	83%	83%
62.1%		66%	76%	65%	63%	47%	66%	55%	51%	66%	63%	63%	65%	63%	66%	66%	66%	63%	47%	63%
81.0%	89%	74%	84%	88%	78%	83%	75%	85%	85%	79%	78%	76%	78%	73%	85%	88%	86%	82%	73%	79%	82%
79.0%	94%	89%	87%	87%	66%	84%	70%	69%	69%	66%	72%	84%	79%	80%	82%	90%	83%	68%	94%	78%	68%
84.8%		92%	87%	83%	82%	76%	88%	88%	91%	89%	84%	87%	90%	77%	84%	88%	75%	84%	76%	89%	86%
90.6%		93%	95%	94%	92%	89%	94%	84%	92%	86%	92%	92%	94%	93%	92%	89%	89%	77%	91%	92%	92%
87.8%		96%	93%	83%	88%	83%	89%	78%	93%	90%	91%	84%	91%	84%	94%	97%	79%	89%	84%	84%	86%
85.6%		83%	93%	94%	94%	79%	91%	93%	87%	91%	93%	79%	83%	82%	84%	85%	86%	75%	77%	79%	84%
83.6%		86%	94%	89%	83%	68%	63%	93%	94%	86%	83%	90%	68%	83%	86%	86%	86%	83%	83%	83%	86%
82.1%		78%	85%	89%	89%	69%	90%	88%	90%	82%	92%	55%	84%	65%	85%	88%	93%	88%	61%	92%	79%
80.6%	79%	84%	79%	83%	76%	71%	86%	83%	82%	85%	80%	87%	79%	87%	83%	81%	79%	79%	79%	72%	78%
86.6%		95%	84%	87%	56%	87%	87%	67%	80%	85%	90%	90%	94%	94%	95%	97%	94%	85%	92%	90%	83%

Model Similarity Dendrogram

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