	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	2nd 80.7%	8th 79.4%	7th 79.8%	5th 80.0%	13th 77.4%	21st 72.9%	9th 79.3%	3rd 80.5%	6th 79.8%	14th 77.3%	4th 80.2%	12th 78.1%	10th 79.2%	17th 76.0%	11th 78.2%	1st 81.0%	19th 75.1%	18th 75.2%	16th 76.3%	20th 73.7%	15th 76.3%
76.4%	79%	78%	68%	70%	79%	63%	72%	79%	79%	74%	79%	83%	80%	77%	77%	78%	79%	74%	79%	80%	77%
81.0%	95%	78%	83%	88%	70%	80%	88%	88%	71%	81%	83%	81%	82%	77%	75%	81%	80%	74%	81%	80%	86%
67.3%	72%	66%	72%	71%	72%	74%	65%	72%	64%	74%	72%	65%	72%	64%	62%	69%	63%	61%	61%	61%	61%
84.7%	90%	83%	89%	89%	86%	82%	90%	84%	90%	89%	85%	79%	85%	79%	85%	85%	84%	79%	76%		85%
89.2%	89%	90%	89%	89%	87%	98%	90%	89%	90%	93%	92%	94%	96%	96%	87%	96%	82%	77%	95%	77%	77%
86.2%	89%	94%	95%	93%	88%	87%	87%	87%	88%	82%	88%	88%	81%	71%	89%	86%	83%	83%	84%	70%	97%
75.1%	75%	71%	76%	81%	75%	72%	77%	83%	85%	70%	78%	75%	70%	75%	63%	81%	73%	83%	77%	68%	70%
76.5%	75%	65%	74%	71%	71%	53%	75%	86%	85%	77%	84%	93%	78%	76%	84%	86%	75%	83%	74%	73%	69%
89.3%	92%	90%	87%	91%	95%	76%	87%	88%	89%	94%	97%	87%	93%	89%	87%	92%	96%	85%	93%	84%	84%
84.0%	86%	86%	87%	90%	86%	85%	88%	81%	83%	85%	87%	88%	86%	79%	87%	90%	71%	73%	85%	80%	82%
77.7%	88%	87%	88%	86%	66%	89%	85%	87%	81%	76%	78%	74%	75%	74%	72%	75%	62%	48%	81%	66%	93%
86.4%	83%	90%	88%	86%	84%	93%	86%	87%	86%	83%	92%	80%	92%	88%	84%	88%	90%	81%	88%	85%	81%
76.9%	72%	80%	72%	67%	76%	73%	82%	79%	82%	74%	79%	79%	84%	85%	73%	74%	81%	78%	74%	81%	70%
79.1%	79%	83%	76%	83%	81%	78%	83%	74%	81%	72%	83%	81%	81%	83%	75%	82%	69%	82%	90%	72%	73%
78.7%	76%	83%	79%	76%	71%	78%	83%	87%	91%	69%	80%	89%	81%	81%	71%	70%	79%	92%	80%	69%	68%
71.1%	78%	71%	77%	78%	73%	52%	68%	75%	69%	64%	72%	67%	74%	62%	78%	78%	80%	63%	70%	72%	72%
52.5%	58%	65%	73%	57%	59%	41%	55%	41%	46%	51%	55%	42%	45%	42%	54%	62%	45%	50%	53%	48%	61%
63.1%	72%	59%	60%	64%	65%	49%	57%	75%	64%	59%	65%	61%	70%	53%	67%	65%	63%	65%	59%	69%	65%
74.3%	82%	62%	88%	82%	62%	61%	83%	71%	73%	81%	77%	65%	75%	69%	86%	86%	83%	71%	60%	69%	75%
78.1%	73%	71%	68%	76%	77%	82%	75%	83%	88%	70%	88%	85%	77%	79%	68%	80%	79%	85%	87%	75%	74%
84.8%	83%	88%	84%	80%	76%	70%	90%	85%	90%	83%	89%	88%	89%	85%	89%	89%	86%	82%	77%	89%	89%
83.1%	77%	81%	80%	78%	86%	79%	83%	86%	88%	84%	86%	82%	85%	89%	80%	81%	85%	88%	78%	84%	85%
72.0%	72%	71%	74%	74%	75%	72%	74%	75%	77%	68%	78%	60%	73%	77%	68%	70%	71%	72%	71%	76%	64%
79.1%	82%	82%	77%	76%	78%	78%	85%	85%	85%	76%	87%	73%	84%	85%	85%	82%	77%	65%	76%	75%	68%
71.8%	76%	73%	70%	75%	75%	70%	73%	73%	75%	70%	76%	76%	72%	73%	62%	75%	63%	81%	78%	58%	64%
72.4%	76%	68%	75%	77%	76%	65%	70%	69%	72%	78%	75%	75%	71%	76%	79%	77%	61%	69%	71%	75%	66%
76.1%	87%	73%	71%	75%	77%	55%	71%	76%	77%	75%	66%	79%	79%	74%	77%	88%	84%	88%	74%	76%	76%
81.6%	91%	81%	80%	81%	91%	64%	83%	92%	86%	78%	83%	78%	80%	73%	92%	91%	82%	87%	66%	74%	80%
74.7%	90%	87%	83%	90%	78%	70%	74%	72%	72%	69%	72%	64%	68%	63%	80%	76%	69%	68%	73%	69%	81%
68.6%	71%	77%	71%	73%	79%	59%	63%	75%	70%	65%	74%	69%	67%	63%	65%	66%	61%	66%	72%		66%
78.6%	79%	83%	82%	78%	77%	72%	82%	83%	83%	75%	75%	84%	80%	80%	77%	77%	80%	77%	80%	77%	69%
92.7%	88%	94%	88%	89%	88%	86%	95%	88%	97%	86%	88%	95%	88%	97%	100%	91%	95%	93%	100%	100%	100%
64.4%	65%	63%	69%	68%	69%	71%	62%	69%	61%	71%	69%	63%	69%	61%	58%	66%	62%	62%	58%	58%	58%
80.3%	88%	82%	82%	91%	86%	68%	82%	84%	84%	81%	84%	80%	67%	66%	95%	95%	68%	78%	66%	74%	86%
70.3%	73%	83%	67%	67%	45%	73%	65%	67%	65%	77%	61%	87%	81%	86%	65%	67%	70%	71%	83%	66%	57%
79.6%	93%	87%	91%	93%	85%	67%	86%	90%	78%	87%	81%	76%	85%	64%	70%	84%	77%	49%	65%	78%	85%
71.5%	73%	79%	71%	74%	66%	62%	78%	85%	77%	66%	74%	83%	70%	68%	74%	75%	63%	68%	69%	64%	62%
87.1%	91%	89%	95%	95%	89%	93%	94%	94%	94%	97%	85%	72%	95%	85%	93%	95%	67%	72%	83%	64%	88%
83.4%	85%	79%	91%	83%	82%	71%	90%	95%	86%	76%	77%	90%	87%	79%	94%	88%	88%	83%	69%		75%
84.3%	88%	82%	88%	87%	88%	91%	81%	88%	80%	91%	88%	82%	88%	80%	78%	86%	79%	77%	77%	77%	95%
79.9%	79%	84%	80%	83%	84%	64%	84%	85%	86%	84%	89%	70%	81%	72%	85%	83%	70%	84%	66%	74%	90%
90.7%	96%	90%	95%	93%	98%	89%	94%	93%	93%	93%	83%	93%	91%	86%	90%	96%	86%	75%	96%	88%	87%
76.8%	66%	86%	77%	72%	56%	78%	77%	57%	70%	78%	95%	83%	77%	86%	81%	81%	70%	93%	86%	72%	72%

Model Similarity Dendrogram

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