	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	3rd 78.3%	4th 78.3%	2nd 79.3%	1st 79.9%	16th 73.5%	21st 65.9%	7th 77.3%	14th 74.7%	13th 75.0%	12th 75.3%	6th 77.5%	17th 72.7%	8th 77.2%	10th 75.7%	11th 75.5%	5th 77.7%	15th 74.4%	20th 69.9%	9th 76.5%	18th 72.4%	19th 72.0%
86.9%	94%	92%	84%	94%	77%	66%	94%	82%	83%	84%	91%	86%	94%	90%	95%	93%	92%	73%	87%	86%	87%
68.7%	67%	60%	72%	76%	43%	67%	62%	65%	53%	61%	69%	91%	69%	71%	85%	75%	81%	67%	81%	65%	63%
85.5%	98%	83%	95%	95%	76%	10%	87%	98%	85%	99%	99%	85%	95%	91%	90%	91%	94%	76%	79%	79%	91%
77.6%	86%	79%	80%	81%	79%	76%	81%	78%	78%	69%	80%	70%	72%	74%	71%	80%	84%	76%	82%	82%	71%
81.8%	93%	86%	86%	86%	78%	88%	87%	89%	79%	82%	74%	77%	78%	79%	91%	86%	84%	66%	87%	87%	54%
80.8%	81%	81%	75%	75%	75%	85%	89%	82%	91%	83%	78%	70%	81%	90%	75%	83%	81%	79%	85%	79%	78%
82.0%	88%	78%	85%	84%	87%	74%	86%	89%	90%	71%	88%	76%	79%	74%	85%	87%	92%	86%	79%	63%	82%
72.6%	78%	77%	78%	78%	62%	58%	80%	79%	71%	89%	74%	77%	73%	68%	77%	72%	64%	63%	63%	74%	69%
74.5%	70%	78%	82%	73%	77%	70%	84%	80%	87%	68%	72%	96%	75%	75%	59%	64%	66%	74%	78%	78%	58%
70.6%	72%	70%	75%	73%	70%	75%	70%	70%	70%	70%	74%	70%	75%	73%	72%	72%	61%	69%	71%	58%	73%
79.5%	83%	93%	91%	89%	81%	91%	75%	93%	73%	61%	81%	71%	69%	61%	69%	80%	88%	57%	88%	84%	91%
80.1%	82%	88%	80%	86%	82%	85%	82%	69%	76%	86%	80%	82%	86%	85%	86%	76%	70%	75%	80%	68%	79%
75.7%	70%	83%	74%	80%	73%	81%	62%	65%	80%	78%	89%	60%	75%	84%	89%	79%	71%	67%	82%	73%	75%
71.2%	72%	81%	76%	67%	58%	68%	87%	71%	72%	55%	73%	68%	68%	70%	67%	82%	85%	65%	85%	70%	56%
79.8%	87%	85%	85%	89%	85%	74%	84%	76%	80%	76%	80%	79%	83%	79%	86%	78%	79%	71%	71%	76%	73%
80.1%	84%	81%	85%	81%	68%	72%	86%	83%	82%	76%	81%	88%	86%	84%	82%	87%	74%	79%	85%	62%	77%
78.6%	87%	87%	80%	86%	94%	70%	78%	69%	74%	83%	79%	55%	78%	76%	82%	86%	67%	72%	82%	83%	82%
67.6%	83%	74%	70%	83%	61%	41%	60%	63%	61%	72%	69%	58%	81%	55%	71%	71%	73%	82%	64%	59%	69%
53.4%	58%	49%	64%	53%	69%	40%	59%	57%	54%	54%	54%	32%	48%	49%	73%	77%	50%	44%	40%	45%	53%
83.7%	85%	71%	85%	85%	93%	85%	88%	86%	89%	79%	94%	89%	84%	89%	83%	75%	78%	81%	86%	68%	84%
71.9%	65%	73%	87%	84%	71%	78%	72%	62%	76%	78%	73%	70%	77%	77%	67%	71%	59%	66%	66%	74%	63%
77.9%	75%	86%	82%	83%	81%	79%	77%	81%	80%	86%	82%	70%	79%	83%	77%	81%	74%	75%	71%	56%	77%
82.1%	76%	76%	83%	76%	100%	93%	96%	73%	74%	79%	94%	67%	100%	88%	76%	76%	80%	67%	89%	95%	67%
74.9%	77%	82%	84%	85%	74%	80%	69%	70%	73%	80%	78%	56%	78%	76%	85%	81%	75%	48%	77%	65%	79%
62.5%	70%	63%	69%	64%	55%	56%	69%	68%	61%	51%	69%	67%	55%	53%	54%	71%	66%	62%	72%	72%	46%
67.0%	64%	76%	75%	68%	65%	65%	65%	59%	67%	69%	71%	65%	65%	76%	70%	61%	53%	77%	70%	72%	55%
71.8%	86%	78%	68%	87%	79%	40%	66%	67%	61%	84%	60%	75%	79%	61%	88%	77%	66%	67%	70%	77%	72%
85.2%	95%	91%	96%	96%	78%	71%	95%	91%	83%	85%	85%	82%	94%	75%	90%	88%	85%	72%	74%	77%	87%
74.1%	80%	85%	82%	90%	85%	73%	69%	69%	70%	69%	72%	67%	72%	65%	76%	82%	72%	67%	69%	70%	73%
68.1%	80%	68%	73%	75%	63%	55%	65%	75%	71%	71%	69%	53%	71%	69%	72%	67%	74%	65%	70%	63%	62%
76.5%	79%	78%	75%	78%	78%	68%	79%	71%	79%	78%	78%	74%	75%	75%	76%	81%	76%	77%	74%	80%	78%
56.4%	51%	66%	53%	53%	72%	10%	61%	51%	64%	48%	48%	64%	53%	57%	59%	56%	55%	56%	71%	79%	57%
64.3%	73%	58%	70%	70%	52%	10%	62%	73%	60%	75%	75%	60%	70%	66%	66%	62%	69%	67%	53%	94%	66%
80.0%	89%	77%	83%	88%	73%	79%	88%	85%	84%	80%	86%	80%	66%	77%	83%	78%	94%	82%	72%	61%	74%
71.1%	80%	76%	67%	78%	53%	80%	59%	62%	73%	83%	61%	64%	84%	87%	70%	76%	63%		77%	87%	43%
70.0%	67%	67%	76%	79%	56%	83%	74%	80%	65%	69%	72%	65%	66%	77%	58%	66%	71%	60%	72%	72%	75%
76.1%	70%	76%	78%	79%	83%	84%	78%	60%	77%	67%	84%	78%	77%	92%	70%	82%	64%	65%	89%	72%	73%
84.2%	98%	85%	98%	90%	93%	90%	98%	87%	90%	91%	90%	75%	96%	78%	83%	77%	62%	51%	78%	73%	86%
79.3%	77%	86%	87%	79%	58%	73%	83%	77%	83%	80%	85%	83%	85%	77%	86%	83%	78%	66%	82%	81%	76%
85.3%	84%	100%	87%	87%	93%	10%	95%	84%	98%	81%	81%	98%	87%	91%	91%	95%	88%	93%	94%	63%	91%
71.6%	73%	82%	84%	81%	62%	69%	80%	78%	67%	75%	80%	84%	81%	81%	0%	75%	82%	82%	83%	34%	71%
78.1%	77%	82%	78%	76%	78%	52%	78%	83%	74%	87%	80%	75%	82%	82%	80%	81%	81%	72%	82%	80%	81%
73.8%	64%	79%	71%	74%	72%	61%	66%	60%	65%	78%	81%	74%	78%	77%	82%	78%	77%	76%	78%	79%	79%

Model Similarity Dendrogram

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