	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	3rd 78.8%	5th 77.5%	1st 79.9%	2nd 79.6%	6th 77.5%	16th 74.7%	7th 77.3%	15th 75.2%	14th 75.4%	4th 78.1%	11th 76.5%	18th 72.6%	12th 76.3%	13th 75.8%	8th 77.0%	10th 76.7%	19th 72.0%	21st 69.7%	9th 76.7%	17th 72.7%	20th 71.3%
78.8%	74%	77%	84%	80%	75%	73%	82%	79%	85%	82%	85%	79%	82%	81%	74%	77%	71%	68%	84%	84%	78%
70.5%	76%	74%	77%	73%	46%	78%	64%	65%	58%	78%	76%	72%	75%	77%	70%	75%	70%	63%	77%	73%	63%
68.4%	71%	65%	71%	58%	71%	71%	68%	62%	58%	68%	71%	71%	66%	62%	68%	66%	72%	66%	65%	67%	99%
78.5%	86%	72%	86%	78%	86%	70%	81%	88%	86%	77%	76%	75%	81%	81%	76%	83%	68%	74%	76%	75%	74%
89.6%	95%	92%	95%	93%	93%	93%	99%	87%	84%	89%	83%	80%	89%	83%	95%	86%	86%	79%	97%	89%	94%
86.3%	84%	88%	83%	84%	92%	95%	86%	95%	90%	86%	90%	80%	81%	82%	78%	86%	97%	93%	82%	77%	83%
83.5%	79%	77%	74%	84%	85%	78%	77%	83%	95%	81%	78%	94%	79%	93%	88%	87%	88%	93%	77%	85%	78%
79.4%	82%	82%	77%	78%	82%	65%	85%	81%	82%	82%	82%	74%	80%	80%	79%	78%	73%	77%	79%	85%	84%
68.0%	61%	67%	64%	66%	84%	70%	74%	78%	80%	69%	72%	57%	70%	67%	58%	61%	72%	78%	69%	55%	55%
76.5%	77%	85%	85%	85%	75%	75%	75%	72%	75%	75%	75%	75%	75%	75%	74%	75%	80%	68%	75%	75%	80%
63.4%	70%	67%	74%	72%	73%	69%	60%	74%	61%	55%	66%	65%	52%	49%	60%	67%	50%	31%	80%	71%	66%
88.0%	87%	79%	91%	86%	85%	87%	89%	96%	93%	91%	87%	85%	89%	95%	91%	93%	82%	90%	85%	86%	80%
65.0%	68%	70%	75%	73%	72%	73%	66%	54%	61%	63%	69%	64%	70%	70%	58%	61%	62%	55%	71%	55%	55%
71.3%	66%	67%	63%	68%	63%	77%	70%	77%	73%	68%	76%	75%	69%	70%	78%	66%	72%	70%	78%	78%	74%
80.2%	82%	78%	84%	82%	87%	82%	85%	73%	74%	75%	85%	69%	78%	82%	83%	79%	80%	82%	82%	80%	82%
75.1%	76%	74%	79%	76%	78%	70%	81%	77%	73%	81%	77%	80%	77%	81%	73%	73%	72%	67%	74%	70%	69%
82.0%	94%	87%	91%	89%	84%	70%	80%	57%	81%	81%	87%	84%	74%	78%	91%	84%	80%	75%	86%	89%	81%
77.0%	84%	80%	83%	86%	94%	57%	70%	76%	79%	82%	63%	77%	79%	63%	86%	78%	80%	72%	75%	72%	80%
56.1%	57%	42%	50%	45%	66%	42%	46%	60%	64%	67%	55%	37%	63%	63%	70%	72%	58%	52%	41%	74%	55%
78.9%	85%	86%	85%	85%	82%	69%	84%	75%	70%	85%	73%	67%	84%	68%	87%	91%	70%	87%	79%	67%	77%
76.7%	79%	83%	83%	83%	76%	86%	79%	74%	78%	85%	78%	68%	78%	91%	72%	70%	70%	62%	84%	82%	50%
71.1%	68%	73%	76%	76%	69%	79%	73%	66%	73%	78%	80%	77%	73%	79%	69%	73%	60%	65%	73%	66%	48%
74.9%	65%	68%	72%	68%	83%	92%	80%	81%	69%	77%	80%	81%	89%	91%	68%	67%	72%	64%	84%	59%	62%
58.3%	73%	67%	72%	74%	64%	64%	52%	50%	53%	60%	59%	39%	52%	53%	64%	55%	54%	46%	65%	56%	52%
77.1%	83%	81%	77%	83%	80%	81%	80%	77%	76%	78%	75%	66%	79%	71%	79%	82%	81%	72%	79%	61%	79%
68.3%	65%	80%	77%	71%	68%	82%	72%	66%	65%	73%	75%	64%	66%	84%	62%	53%	53%	69%	75%	59%	55%
77.2%	82%	80%	83%	85%	78%	56%	84%	80%	74%	89%	71%	80%	74%	64%	83%	78%	78%	69%	80%	78%	75%
73.9%	79%	79%	76%	77%	47%	69%	77%	76%	68%	79%	82%	72%	77%	72%	75%	75%	76%	69%	73%	81%	73%
69.9%	76%	80%	96%	89%	75%	66%	73%	68%	68%	58%	69%	55%	61%	60%	72%	73%	61%	64%	71%	60%	73%
79.7%	83%	80%	93%	98%	85%	71%	72%	80%	78%	81%	84%	71%	80%	74%	84%	85%	78%	63%	74%	77%	83%
76.4%	83%	74%	74%	80%	73%	78%	69%	68%	72%	84%	78%	80%	74%	78%	82%	81%	64%	70%	75%	87%	80%
90.0%	89%	94%	88%	98%	88%	88%	91%	98%	98%	91%	88%	88%	93%	97%	91%	92%	87%	93%	94%	85%	59%
70.2%	76%	70%	76%	63%	76%	76%	73%	67%	63%	73%	76%	76%	71%	67%	64%	72%	77%	63%	70%	67%	59%
74.1%	85%	73%	77%	83%	78%	65%	72%	79%	75%	76%	67%	67%	74%	65%	81%	75%	74%	75%	68%	74%	74%
79.0%	92%	90%	90%	88%	74%	70%	78%	80%	74%	66%	78%	66%	77%	72%	79%	85%	75%	86%	83%	70%	85%
79.4%	90%	86%	89%	90%	58%	78%	87%	79%	70%	87%	83%	77%	80%	78%	78%	85%	81%	69%	74%		69%
69.6%	69%	69%	75%	73%	73%	71%	74%	67%	66%	74%	70%	66%	70%	70%	72%	68%	69%	61%	67%	68%	70%
78.0%	99%	82%	84%	85%	91%	93%	96%	85%	88%	94%	73%	70%	88%	78%	84%	78%	59%	55%	83%	37%	37%
77.5%	83%	84%	86%	83%	77%	79%	80%	65%	79%	86%	82%	81%	84%	79%	81%	74%	61%	63%	77%	81%	62%
89.3%	79%	94%	88%	98%	88%	88%	91%	98%	98%	91%	88%	88%	93%	97%	91%	93%	87%	93%	94%	53%	85%
69.4%	72%	78%	66%	66%	83%	69%	76%	72%	81%	82%	72%	64%	74%	68%	74%	79%	30%	30%	62%	79%	80%
74.5%	76%	76%	70%	76%	78%	57%	83%	74%	66%	74%	80%	78%	69%	83%	80%	74%	77%	78%	67%	76%	72%
87.5%	90%	84%	96%	93%	96%	90%	88%	76%	87%	88%	74%	86%	94%	88%	87%	92%	89%	79%	94%	89%	78%

Model Similarity Dendrogram

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