	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	1st 83.1%	3rd 81.4%	5th 81.0%	4th 81.4%	6th 80.7%	19th 75.5%	11th 80.0%	9th 80.1%	16th 77.8%	7th 80.4%	12th 79.9%	20th 75.3%	10th 80.1%	13th 79.0%	8th 80.3%	2nd 81.9%	15th 77.9%	21st 74.5%	14th 78.5%	18th 75.9%	17th 77.1%
86.0%	89%	87%	86%	85%	88%	76%	86%	89%	86%	86%	88%	91%	89%	91%	85%	84%	87%	75%	81%	90%	87%
89.2%	87%	88%	90%	94%	78%	94%	94%	91%	70%	93%	93%	94%	88%	93%	92%	90%	96%	74%	95%	88%	91%
69.1%	68%	72%	72%	72%	66%	77%	66%	72%	68%	72%	72%	74%	67%	72%	69%	67%	68%	68%	64%	63%	63%
67.4%	73%	70%	63%	62%	72%	65%	80%	67%	61%	53%	72%	48%	72%	69%	64%	71%	62%	82%	81%	61%	67%
88.9%	85%	89%	90%	84%	90%	87%	86%	88%	85%	91%	90%	93%	91%	89%	83%	93%	90%	92%	90%	97%	84%
82.6%	85%	92%	86%	87%	84%	76%	89%	91%	87%	83%	78%	81%	79%	73%	83%	83%	85%	86%	77%	68%	82%
84.0%	86%	77%	85%	93%	87%	82%	84%	87%	87%	94%	88%	92%	87%	76%	76%	88%	91%	75%	79%	70%	81%
77.3%	78%	69%	74%	76%	80%	63%	79%	75%	81%	85%	73%	85%	81%	85%	68%	83%	82%	81%	81%	80%	64%
80.4%	83%	75%	77%	77%	84%	70%	76%	84%	83%	81%	84%	89%	78%	84%	78%	84%	89%	77%	84%	84%	68%
62.0%	61%	71%	58%	66%	66%	65%	76%	61%	58%	47%	70%	44%	65%	65%	63%	57%	71%	64%	89%	42%	44%
87.1%	90%	92%	92%	83%	93%	82%	92%	86%	90%	90%	90%	92%	90%	90%	85%	86%	89%	63%	88%	86%	81%
59.3%	62%	77%	52%	65%	64%	59%	57%	61%	55%	50%	60%	41%	58%	63%	54%	67%	59%	63%	75%	55%	48%
86.0%	90%	94%	94%	94%	94%	93%	74%	76%	82%	88%	84%	61%	92%	85%	95%	95%	87%	59%	87%	92%	91%
87.3%	95%	94%	94%	78%	81%	84%	95%	89%	82%	83%	87%	78%	91%	92%	91%	85%	83%	87%	86%	85%	93%
85.0%	92%	93%	91%	91%	85%	86%	81%	86%	84%	92%	82%	70%	89%	89%	92%	89%	81%	64%	83%	80%	86%
79.0%	82%	79%	81%	89%	86%	64%	73%	85%	78%	82%	80%	79%	78%	76%	74%	81%	79%	86%	68%	80%	80%
65.8%	76%	74%	68%	73%	74%	73%	66%	55%	67%	64%	56%	66%	58%	56%	74%	68%	67%	56%	68%	57%	66%
63.7%	73%	67%	63%	71%	68%	49%	63%	71%	66%	64%	68%	69%	66%	60%	59%	61%	55%	55%	66%	57%	67%
76.4%	80%	63%	84%	78%	69%	58%	89%	77%	70%	78%	78%	68%	86%	69%	84%	90%	81%	75%	63%	80%	85%
87.0%	90%	82%	87%	86%	90%	94%	87%	94%	90%	92%	92%	86%	89%	87%	79%	89%	90%	74%	86%	75%	89%
89.4%	96%	88%	90%	88%	90%	75%	96%	97%	92%	94%	92%	84%	95%	90%	93%	94%	84%	84%	79%	89%	88%
88.7%	90%	95%	89%	92%	91%	78%	95%	85%	86%	95%	91%	77%	94%	89%	96%	96%	85%	82%	79%	85%	92%
78.7%	92%	76%	83%	84%	76%	68%	88%	75%	76%	81%	77%	65%	77%	74%	84%	86%	76%	74%	81%	81%	79%
88.3%	93%	94%	95%	94%	86%	92%	90%	92%	86%	93%	88%	67%	92%	83%	90%	94%	86%	72%	85%	93%	90%
87.7%	91%	90%	90%	81%	89%	92%	96%	88%	84%	83%	89%	80%	90%	89%	90%	89%	85%	76%	87%	87%	95%
80.8%	91%	83%	81%	83%	83%	76%	77%	73%	76%	87%	83%	73%	82%	81%	88%	81%	77%	74%	80%	81%	86%
72.9%	82%	72%	76%	79%	75%	53%	66%	77%	76%	76%	65%	77%	71%	66%	77%	80%	74%	71%	68%	73%	77%
80.4%	83%	78%	80%	79%	88%	64%	81%	84%	87%	86%	84%	87%	80%	71%	86%	85%	75%	80%	74%	78%	79%
55.8%	60%	69%	58%	69%	50%	46%	53%	57%	52%	48%	60%	36%	52%	53%	60%	61%	52%	63%	71%	56%	45%
67.9%	63%	72%	71%	72%	61%	63%	55%	59%	70%	68%	74%	67%	62%	73%	68%	72%	76%	72%	74%	69%	64%
86.1%	94%	86%	95%	82%	92%	87%	84%	83%	82%	86%	81%	74%	85%	90%	94%	93%	76%	80%	87%	84%	94%
78.1%	79%	76%	76%	76%	82%	70%	82%	76%	79%	75%	76%	73%	80%	76%	80%	80%	79%	79%	84%	82%	80%
60.8%	58%	63%	63%	63%	58%	69%	57%	63%	60%	63%	63%	65%	59%	63%	60%	60%	60%	61%	56%	57%	56%
85.9%	90%	82%	85%	92%	92%	80%	77%	95%	92%	90%	86%	88%	82%	84%	89%	94%	88%	75%	73%	88%	81%
65.5%	74%	78%	66%	67%	59%	61%	54%	61%	58%	63%	66%	66%	77%	84%	56%	62%	61%	74%	84%	56%	48%
80.5%	88%	87%	93%	89%	81%	81%	85%	90%	69%	82%	80%	78%	83%	76%	80%	74%	75%	78%	74%	70%	77%
88.0%	95%	87%	87%	89%	91%	92%	90%	92%	90%	91%	83%	81%	90%	91%	95%	93%	85%	67%	86%	86%	88%
90.2%	88%	93%	95%	97%	95%	92%	95%	92%	90%	95%	94%	77%	95%	92%	99%	94%	74%	96%	80%	75%	86%
81.8%	98%	84%	90%	85%	89%	72%	89%	82%	79%	91%	80%	79%	81%	77%	89%	85%	82%	71%	68%	74%	73%
93.4%	93%	96%	96%	96%	90%	98%	90%	96%	93%	96%	96%	98%	92%	96%	92%	92%	93%	93%	88%	90%	88%
86.0%	86%	85%	88%	93%	96%	78%	94%	88%	87%	94%	85%	91%	83%	82%	92%	93%	72%	72%	74%	85%	89%
72.4%	76%	75%	71%	71%	75%	73%	76%	75%	76%	77%	74%	75%	75%	76%	65%	69%	71%	68%	72%	63%	67%
79.5%	90%	88%	76%	74%	80%	88%	75%	81%	77%	75%	84%	77%	75%	79%	82%	83%	71%	86%	80%	71%	78%

Model Similarity Dendrogram

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