	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	- -	5th 83.9%	20th 74.9%	2nd 84.7%	3rd 84.7%	17th 78.2%	9th 81.9%	11th 80.7%	8th 81.9%	10th 81.5%	4th 84.1%	13th 80.3%	7th 83.6%	14th 80.2%	6th 83.8%	1st 84.9%	16th 78.7%	19th 75.2%	12th 80.5%	18th 76.2%	15th 79.6%
86.5%		86%	82%	84%	97%	74%	85%	85%	87%	85%	91%	90%	96%	78%	89%	91%	88%	88%	90%	82%	83%
88.1%		84%	90%	92%	81%	91%	91%	82%	81%	90%	91%	93%	93%	94%	93%	95%	92%	74%	93%	81%	82%
72.5%		73%	0%	82%	75%	78%	73%	76%	67%	82%	78%	75%	80%	73%	73%	72%	95%	80%	73%	72%	72%
86.9%		85%	86%	88%	87%	84%	88%	90%	88%	89%	84%	83%	89%	84%	89%	89%	80%	88%	84%	91%	92%
87.1%		90%	83%	88%	90%	84%	85%	88%	91%	89%	98%	94%	89%	88%	93%	91%	96%	88%	81%	60%	76%
87.8%		95%	89%	94%	92%	95%	90%	93%	90%	86%	84%	74%	92%	75%	85%	89%	94%	84%	90%	74%	91%
82.4%		77%	81%	88%	92%	71%	80%	89%	91%	70%	91%	90%	83%	81%	77%	89%	87%	88%	80%	71%	72%
83.8%		82%	77%	85%	77%	59%	79%	94%	94%	84%	90%	83%	86%	77%	93%	94%	92%	83%	72%	82%	92%
84.3%		81%	81%	81%	87%	70%	78%	79%	79%	93%	94%	91%	93%	88%	81%	91%	88%	73%	81%	96%	81%
86.1%		98%	87%	87%	93%	95%	86%	84%	80%	84%	87%	93%	86%	88%	83%	89%	74%	68%	91%	82%	86%
80.5%		89%	90%	90%	79%	89%	78%	85%	83%	76%	89%	89%	68%	75%	82%	78%	75%	57%	84%	72%	83%
88.8%		89%	88%	94%	93%	94%	76%	94%	91%	87%	84%	91%	94%	88%	90%	92%	85%	81%	90%	85%	91%
87.6%		95%	83%	87%	90%	90%	90%	81%	91%	91%	94%	72%	90%	92%	94%	97%	83%	65%	85%	87%	95%
79.1%		88%	82%	84%	86%	74%	91%	74%	76%	74%	82%	83%	84%	87%	73%	93%	62%	75%	88%	63%	63%
86.3%		91%	87%	86%	82%	84%	89%	85%	90%	80%	90%	83%	90%	91%	85%	89%	87%	82%	85%	87%	82%
81.5%		86%	88%	88%	89%	62%	81%	90%	73%	84%	81%	80%	85%	78%	85%	83%	68%	85%	87%	83%	75%
64.3%		73%	76%	73%	70%	70%	69%	59%	58%	62%	61%	56%	56%	56%	71%	74%	59%	41%	70%	64%	68%
67.8%		69%	72%	81%	67%	53%	59%	66%	63%	60%	73%	64%	77%	60%	84%	71%	68%	67%	70%	66%	67%
58.1%		48%	76%	61%	64%	54%	62%	54%	56%	61%	57%	47%	63%	50%	81%	70%	54%	44%	44%	62%	53%
85.4%		71%	76%	84%	91%	86%	89%	82%	95%	82%	95%	95%	86%	91%	81%	79%	84%	83%	94%	75%	90%
87.5%		94%	90%	88%	91%	81%	94%	81%	94%	89%	93%	87%	95%	88%	90%	89%	73%	86%	79%	83%	86%
87.0%		91%	85%	85%	90%	83%	89%	81%	90%	90%	91%	80%	87%	87%	91%	93%	89%	81%	77%	88%	92%
81.7%		77%	75%	75%	94%	87%	89%	88%	80%	80%	88%	87%	80%	92%	77%	78%	80%	80%	77%	76%	74%
86.6%		91%	89%	92%	91%	93%	83%	87%	91%	91%	94%	69%	90%	83%	94%	97%	86%	63%	79%	83%	85%
78.5%		85%	82%	84%	86%	79%	84%	72%	77%	78%	94%	80%	83%	86%	77%	81%	63%	71%	85%	62%	62%
75.2%		75%	80%	80%	81%	72%	75%	70%	76%	77%	77%	79%	80%	76%	79%	79%	63%	67%	80%	66%	71%
72.7%		74%	69%	78%	77%	51%	63%	72%	73%	76%	60%	73%	74%	64%	88%	83%	79%	76%	69%	76%	79%
82.3%		85%	77%	86%	91%	64%	82%	86%	90%	82%	83%	79%	86%	70%	95%	96%	78%	89%	64%	86%	78%
76.8%		92%	91%	95%	92%	71%	86%	70%	70%	73%	72%	72%	70%	72%	76%	78%	68%	72%	69%	72%	74%
78.8%		87%	76%	89%	94%	77%	66%	84%	83%	76%	80%	70%	77%	75%	80%	88%	92%	65%	83%	68%	65%
85.8%		83%	84%	84%	92%	83%	84%	79%	85%	87%	89%	79%	87%	88%	91%	90%	84%	87%	88%	86%	85%
71.7%		80%	0%	70%	77%	74%	80%	77%	85%	71%	74%	77%	73%	79%	80%	70%	58%	68%	80%	80%	80%
65.1%		67%	0%	76%	69%	72%	67%	69%	61%	76%	72%	69%	73%	67%	66%	67%	88%	62%	72%	43%	66%
84.7%		85%	84%	92%	94%	72%	91%	88%	90%	88%	87%	84%	75%	71%	88%	89%	93%	72%	72%	85%	93%
75.8%		86%	65%	82%	65%	89%	65%	77%	75%	70%	72%	82%	89%	88%	73%	60%	62%	84%	82%	89%	61%
84.9%		91%	93%	87%	77%	90%	89%	87%	88%	94%	89%	83%	93%	82%	70%	85%	78%	72%	82%	82%	86%
85.4%		87%	85%	85%	85%	84%	88%	72%	89%	88%	88%	81%	90%	88%	78%	90%	79%	78%	90%	89%	94%
84.9%		98%	97%	98%	92%	94%	90%	89%	91%	90%	92%	75%	97%	72%	94%	88%	63%	62%	83%	45%	87%
83.4%		86%	88%	93%	84%	76%	89%	90%	82%	87%	82%	79%	83%	78%	93%	90%	84%	77%	71%	84%	73%
89.8%		99%	0%	92%	99%	95%	99%	98%	93%	92%	96%	99%	94%	99%	98%	99%	79%	94%	99%	73%	98%
86.7%		88%	89%	89%	94%	70%	91%	88%	89%	87%	94%	81%	87%	85%	89%	94%	79%	79%	87%	81%	93%
78.0%		82%	74%	77%	75%	71%	81%	82%	79%	86%	74%	84%	77%	84%	78%	77%	77%	71%	82%	74%	74%
74.1%		76%	74%	67%	68%	79%	77%	55%	68%	67%	83%	79%	76%	79%	77%	74%	79%	82%	78%	71%	73%

Model Similarity Dendrogram

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