	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 81.1%	5th 79.5%	12th 77.2%	1st 81.3%	15th 76.3%	20th 72.9%	11th 77.3%	6th 79.3%	9th 77.6%	10th 77.3%	4th 80.0%	18th 75.3%	7th 79.3%	8th 78.0%	21st 70.1%	3rd 80.5%	17th 75.5%	19th 75.2%	13th 76.6%	16th 75.5%	14th 76.5%
76.7%	82%	77%	67%	77%	78%	61%	74%	78%	75%	71%	77%	62%	83%	72%	81%	79%	81%	84%	81%	90%	81%
77.4%	74%	70%	78%	83%	58%	95%	75%	73%	59%	77%	81%	87%	80%	85%	89%	79%	85%	59%	83%	77%	79%
72.0%	77%	69%	62%	81%	62%	77%	66%	77%	74%	77%	81%	79%	74%	72%	70%	72%	70%	62%	69%	71%	71%
91.3%	94%	87%	92%	90%	95%	89%	92%	94%	95%	93%	92%	91%	93%	86%	94%	96%	86%	83%	90%	96%	90%
82.6%	87%	85%	79%	75%	74%	80%	79%	92%	75%	83%	93%	87%	84%	88%	88%	84%	84%	80%	83%	86%	69%
85.2%	87%	89%	90%	94%	83%	86%	83%	83%	86%	85%	89%	73%	86%	81%	83%	85%	86%	91%	83%	80%	87%
71.4%	71%	66%	75%	87%	75%	59%	66%	85%	78%	67%	74%	51%	68%	68%	66%	72%	74%	80%	78%		67%
71.8%	70%	74%	66%	68%	64%	44%	74%	84%	85%	68%	80%	74%	76%	67%	82%	77%	74%	81%	56%	70%	74%
72.3%	85%	71%	61%	63%	55%	52%	66%	65%	67%	74%	80%	88%	81%	77%	89%	87%	71%	68%	68%	75%	75%
86.1%	90%	91%	86%	89%	84%	96%	90%	85%	78%	88%	87%	93%	88%	87%	85%	89%	70%	78%	91%	77%	86%
83.6%	90%	88%	89%	88%	81%	82%	89%	89%	86%	80%	89%	84%	77%	78%	85%	84%	93%	57%	81%	82%	83%
86.6%	94%	89%	88%	91%	85%	92%	78%	89%	85%	87%	86%	90%	85%	86%	84%	86%	73%	86%	84%	87%	94%
83.6%	85%	84%	79%	80%	77%	84%	90%	91%	87%	87%	85%	84%	87%	89%	77%	78%	86%	82%	73%	88%	82%
79.5%	81%	80%	84%	87%	87%	69%	88%	81%	89%	78%	87%	65%	78%	90%	77%	85%	65%	76%	83%	69%	70%
87.3%	95%	90%	84%	95%	90%	87%	85%	73%	74%	89%	92%	78%	92%	94%	90%	94%	73%	87%	90%	92%	89%
70.1%	77%	77%	70%	80%	70%	54%	65%	82%	65%	64%	67%	60%	76%	66%	69%	73%	78%	80%	68%	66%	66%
62.6%	66%	83%	74%	66%	54%	61%	63%	52%	59%	63%	69%	68%	63%	63%	72%	64%	43%	49%	63%	56%	63%
55.2%	62%	58%	53%	62%	53%	41%	50%	55%	50%	49%	51%	39%	57%	46%	61%	60%	80%	64%	59%	52%	57%
70.9%	83%	60%	85%	84%	74%	56%	78%	71%	74%	74%	69%	56%	70%	82%	83%	84%	54%	63%	61%		56%
72.4%	71%	62%	60%	70%	76%	76%	70%	87%	90%	72%	81%	92%	75%	80%	0%	76%	90%	70%	78%	67%	78%
83.0%	83%	86%	76%	81%	73%	71%	87%	90%	89%	82%	79%	93%	82%	79%	82%	96%	82%	89%	74%	77%	92%
85.1%	86%	86%	85%	82%	89%	77%	88%	89%	88%	83%	87%	87%	89%	85%	86%	87%	87%	85%	70%	82%	89%
80.1%	78%	75%	78%	83%	83%	89%	88%	85%	78%	74%	90%	67%	75%	90%	85%	78%	77%	81%	77%	77%	74%
76.6%	77%	79%	78%	86%	79%	77%	91%	89%	88%	79%	80%	76%	86%	89%	0%	82%	87%	77%	69%	59%	81%
77.6%	85%	77%	80%	84%	89%	74%	84%	82%	85%	74%	89%	63%	79%	83%	74%	84%	56%	74%	85%	64%	64%
71.6%	78%	73%	70%	76%	75%	66%	68%	58%	71%	74%	74%	71%	76%	71%	64%	72%	74%	75%	74%	75%	69%
62.6%	72%	67%	60%	66%	66%	44%	54%	60%	64%	58%	54%	66%	66%	57%	71%	68%	62%	65%	63%	68%	64%
81.6%	82%	91%	80%	84%	78%	67%	83%	93%	86%	82%	87%	81%	84%	73%	89%	93%	82%	94%	75%	65%	65%
75.6%	87%	93%	84%	92%	90%	69%	77%	72%	70%	70%	70%	67%	72%	70%	75%	71%	70%	73%	71%	69%	75%
61.3%	62%	76%	65%	69%	73%	49%	51%	71%	56%	53%	66%	60%	64%	57%	60%	58%	55%	71%	62%	52%	58%
78.1%	82%	77%	78%	78%	84%	80%	76%	69%	75%	83%	81%	70%	80%	83%	83%	85%	70%	69%	82%	72%	84%
80.0%	80%	88%	95%	76%	95%	80%	91%	80%	83%	80%	76%	78%	83%	85%	0%	85%	87%	78%	88%	86%	86%
62.1%	65%	61%	55%	73%	55%	70%	59%	69%	66%	70%	73%	71%	67%	65%	0%	67%	63%	71%	62%	59%	63%
77.2%	83%	79%	78%	90%	89%	66%	80%	88%	87%	79%	80%	55%	71%	68%	94%	86%	73%	72%	69%	66%	68%
67.1%	78%	79%	57%	74%	42%	73%	56%	68%	66%	71%	54%	74%	80%	74%	43%	58%	55%	81%	84%	87%	55%
85.0%	93%	89%	95%	96%	83%	78%	88%	93%	85%	93%	84%	85%	86%	76%	83%	86%	85%	67%	74%	82%	83%
82.3%	89%	77%	83%	83%	87%	83%	85%	67%	75%	80%	83%	80%	86%	88%	77%	85%	79%	73%	88%	85%	95%
85.7%	87%	91%	90%	86%	78%	85%	83%	89%	82%	84%	92%	76%	88%	87%	93%	91%	79%	68%	100%	84%	87%
82.7%	92%	93%	95%	92%	90%	76%	93%	86%	88%	90%	86%	87%	84%	82%	0%	93%	85%	75%	74%	84%	92%
92.2%	93%	89%	82%	98%	82%	98%	87%	98%	95%	98%	98%	100%	95%	93%	91%	93%	91%	82%	90%	92%	92%
87.0%	89%	88%	92%	93%	93%	77%	86%	92%	87%	92%	88%	74%	89%	77%	92%	91%	83%	83%	89%	84%	88%
78.3%	75%	85%	74%	74%	75%	70%	76%	81%	80%	79%	77%	81%	85%	86%	81%	78%	76%	69%	82%	78%	82%
69.6%	70%	70%	69%	70%	56%	73%	71%	56%	60%	71%	81%	73%	71%	79%	66%	70%	71%	82%	70%	67%	66%

Model Similarity Dendrogram

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