	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 84.8%	15th 80.6%	4th 83.2%	3rd 83.4%	12th 81.3%	21st 76.2%	8th 81.9%	11th 81.3%	7th 82.0%	6th 82.6%	13th 81.1%	18th 78.0%	14th 80.8%	19th 77.9%	2nd 83.7%	5th 83.1%	16th 80.0%	20th 77.8%	17th 78.2%	9th 81.8%	10th 81.5%
81.4%	81%	87%	83%	85%	83%	84%	81%	85%	78%	81%	89%	70%	81%	80%	84%	82%	74%	69%	84%	88%	81%
71.0%	69%	76%	68%	72%	56%	87%	73%	67%	68%	66%	79%	82%	73%	89%	69%	60%	66%	59%	78%	70%	63%
75.9%	81%	81%	69%	72%	78%	61%	87%	69%	73%	81%	78%	100%	78%	61%	81%	81%	81%	61%	61%	78%	81%
87.4%	87%	78%	92%	89%	87%	79%	87%	84%	88%	86%	87%	89%	90%	89%	89%	87%	85%	91%	82%	95%	95%
82.1%	82%	78%	82%	91%	78%	78%	86%	88%	80%	87%	78%	78%	78%	78%	88%	94%	80%	78%	78%	78%	87%
84.7%	89%	91%	87%	89%	98%	81%	82%	90%	87%	84%	82%	87%	79%	83%	85%	84%	71%	79%	79%	83%	89%
87.1%	91%	90%	85%	91%	85%	80%	85%	89%	90%	87%	84%	82%	90%	86%	89%	85%	90%	88%	82%	88%	92%
73.7%	78%	70%	74%	73%	72%	59%	68%	78%	73%	81%	67%	74%	72%	65%	82%	84%	70%	76%	67%	84%	81%
70.9%	70%	62%	64%	63%	77%	60%	74%	73%	72%	76%	70%	46%	80%	76%	75%	77%	76%	80%	70%	70%	77%
88.6%	89%	89%	93%	95%	89%	89%	81%	75%	93%	91%	89%	89%	91%	89%	92%	92%	84%	78%	89%	89%	95%
78.0%	81%	89%	93%	84%	78%	81%	90%	89%	76%	69%	91%	90%	72%	75%	74%	88%	54%	56%	75%	87%	46%
83.2%	93%	89%	90%	90%	83%	79%	80%	88%	88%	80%	72%	87%	74%	76%	87%	86%	79%	64%	90%	84%	89%
85.7%	87%	90%	87%	87%	87%	77%	86%	89%	86%	85%	87%	83%	83%	87%	85%	85%	87%	84%	87%	87%	83%
88.6%	92%	88%	89%	90%	88%	84%	87%	84%	89%	90%	91%	82%	94%	91%	91%	88%	87%	90%	86%	89%	91%
88.0%	92%	89%	90%	89%	88%	92%	89%	93%	88%	90%	91%	88%	88%	79%	81%	83%	84%	89%	90%	88%	88%
86.0%	91%	77%	89%	86%	90%	76%	85%	89%	88%	85%	88%	97%	82%	82%	87%	81%	89%	87%	91%	77%	89%
72.7%	78%	80%	78%	78%	77%	67%	71%	47%	66%	77%	77%	75%	62%	64%	78%	77%	79%	75%	70%		79%
75.0%	83%	72%	74%	77%	72%	76%	74%	75%	75%	78%	75%	52%	76%	68%	79%	79%	77%	92%	66%	80%
68.3%	74%	58%	77%	62%	83%	50%	67%	64%	72%	75%	65%	47%	75%	66%	82%	79%	75%	72%	50%	77%	65%
86.5%	98%	76%	94%	95%	94%	85%	91%	93%	93%	92%	72%	72%	89%	82%	83%	92%	84%	85%	93%	78%	75%
88.6%	95%	81%	91%	94%	87%	86%	83%	87%	88%	95%	88%	88%	96%	91%	94%	96%	85%	81%	84%	79%	91%
87.4%	87%	91%	82%	86%	87%	79%	89%	91%	85%	87%	82%	88%	89%	90%	87%	87%	91%	83%	94%	91%	90%
76.9%	70%	74%	80%	78%	73%	84%	83%	78%	76%	82%	82%	67%	71%	82%	81%	78%	64%	88%	81%	75%	68%
86.5%	84%	79%	82%	89%	87%	84%	91%	87%	87%	90%	86%	87%	92%	87%	84%	86%	91%	87%	87%	88%	81%
87.8%	91%	86%	92%	88%	84%	91%	91%	89%	88%	90%	88%	78%	85%	84%	89%	89%	87%	85%	86%	90%	92%
77.5%	82%	81%	77%	78%	80%	71%	77%	73%	74%	77%	81%	77%	69%	71%	75%	78%	76%	75%	86%	79%	90%
80.7%	88%	70%	90%	84%	86%	79%	87%	84%	83%	83%	71%	71%	80%	83%	89%	78%	80%	76%	74%	74%	85%
80.9%	86%	80%	78%	81%	93%	66%	84%	91%	94%	84%	78%	79%	79%	70%	91%	84%	83%	74%	73%	79%	72%
74.8%	79%	87%	87%	85%	70%	73%	80%	64%	75%	69%	67%	67%	66%	66%	85%	81%	71%	56%	78%	73%	91%
79.2%	88%	78%	82%	84%	87%	63%	75%	91%	83%	75%	76%	77%	75%	77%	83%	78%	84%	86%	79%	71%	71%
86.4%	89%	85%	91%	88%	83%	93%	82%	89%	87%	87%	90%	86%	87%	81%	85%	85%	85%	83%	88%	85%	85%
67.9%	65%	65%	67%	70%	82%	50%	75%	80%	73%	65%	82%	61%	65%	61%	65%	65%	78%	65%	61%	65%	65%
65.8%	67%	66%	58%	61%	67%	67%	87%	57%	62%	67%	67%	87%	67%	50%	67%	67%	67%	50%	67%	67%	67%
82.3%	89%	77%	86%	89%	85%	77%	80%	85%	84%	84%	82%	78%	81%	75%	85%	84%	86%	84%	75%	80%	83%
71.0%	83%	82%	78%	77%	43%	74%	65%	58%	69%	63%	69%	77%	71%	69%	85%	72%	68%	71%	81%		65%
83.0%	92%	85%	91%	85%	69%	70%	82%	91%	91%	94%	88%	75%	85%	74%	85%	84%	74%	78%	73%	89%	89%
88.2%	95%	85%	89%	89%	97%	93%	91%	93%	90%	93%	85%	81%	89%	81%	89%	95%	83%	76%	84%	88%	86%
87.0%	96%	88%	88%	86%	90%	73%	90%	89%	88%	95%	93%	78%	86%	78%	88%	85%	93%	87%	78%	89%	89%
85.9%	92%	85%	93%	92%	79%	80%	91%	95%	85%	93%	88%	79%	91%	80%	87%	87%	80%	80%	75%	90%	82%
86.0%	91%	91%	96%	93%	82%	82%	67%	87%	87%	91%	82%	78%	91%	78%	91%	91%	94%	82%	78%	82%	91%
75.6%	77%	69%	71%	78%	92%	56%	75%	81%	87%	74%	84%	51%	81%	70%	74%	79%	85%	82%	51%	89%	81%
83.9%	86%	85%	85%	85%	78%	77%	91%	85%	85%	91%	84%	90%	85%	94%	84%	82%	79%	77%	80%	82%	77%
83.6%	87%	86%	84%	87%	70%	82%	82%	62%	84%	82%	81%	84%	88%	91%	93%	98%	82%	88%	80%	80%	84%

Model Similarity Dendrogram

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