	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	2nd 80.7%	3rd 80.3%	6th 79.4%	5th 80.0%	13th 77.3%	21st 73.2%	10th 79.2%	1st 80.8%	9th 79.3%	12th 77.9%	7th 79.3%	13th 77.3%	7th 79.3%	17th 76.1%	11th 78.3%	4th 80.2%	15th 77.0%	20th 73.5%	16th 76.3%	19th 73.7%	18th 75.5%
75.6%	79%	78%	68%	71%	79%	53%	72%	84%	77%	70%	83%	83%	80%	68%	80%	80%	85%	67%	80%	73%	77%
81.5%	92%	78%	83%	88%	80%	81%	88%	88%	71%	84%	85%	81%	85%	74%	85%	84%	88%	72%	81%	70%	74%
67.4%	72%	66%	72%	71%	74%	74%	64%	72%	62%	74%	72%	72%	72%	64%	61%	65%	63%	63%	61%	61%	61%
85.2%	89%	83%	89%	89%	86%	84%	90%	89%	90%	89%	89%	82%	85%	74%	84%	85%	84%	75%	80%	86%	88%
90.6%	90%	98%	83%	89%	90%	96%	94%	94%	86%	90%	92%	93%	90%	96%	94%	99%	90%	79%	92%	79%	89%
83.8%	89%	94%	93%	93%	88%	88%	87%	86%	78%	85%	81%	79%	87%	71%	81%	88%	74%	83%	86%	58%	91%
75.6%	75%	71%	76%	76%	75%	75%	74%	76%	85%	69%	76%	79%	77%	75%	71%	73%	85%	75%	77%	75%	73%
77.3%	75%	73%	67%	71%	71%	57%	72%	86%	87%	77%	81%	87%	81%	81%	83%	89%	87%	80%	72%	73%	74%
90.2%	92%	90%	87%	87%	94%	76%	84%	94%	89%	97%	96%	91%	94%	94%	89%	95%	94%	94%	89%	84%	84%
83.2%	86%	86%	87%	90%	84%	85%	88%	79%	80%	85%	85%	88%	87%	79%	82%	84%	77%	71%	79%	83%	83%
79.2%	85%	88%	88%	86%	69%	85%	85%	86%	81%	76%	86%	74%	77%	74%	77%	76%	73%	54%	85%	73%	86%
85.9%	85%	90%	88%	85%	92%	93%	86%	85%	85%	86%	85%	80%	85%	91%	85%	85%	81%	80%	87%	91%	78%
76.7%	73%	80%	69%	67%	73%	72%	81%	79%	79%	71%	76%	79%	83%	85%	74%	75%	85%	84%	75%	79%	71%
78.7%	76%	83%	76%	77%	79%	70%	83%	76%	81%	75%	83%	78%	81%	83%	77%	82%	73%	81%	86%		74%
77.5%	70%	83%	80%	72%	71%	66%	83%	87%	91%	67%	79%	89%	79%	80%	69%	71%	85%	87%	80%	76%	63%
70.2%	76%	71%	77%	79%	68%	57%	68%	78%	69%	69%	71%	67%	74%	65%	71%	75%	68%	68%	67%	68%	69%
51.6%	56%	69%	65%	57%	52%	53%	55%	41%	46%	53%	46%	41%	41%	42%	65%	66%	40%	47%	53%	47%	48%
63.2%	72%	59%	62%	64%	58%	38%	57%	75%	65%	60%	63%	69%	62%	53%	65%		77%	63%	59%	74%	69%
70.9%	79%	62%	88%	82%	46%	64%	79%	70%	73%	82%	71%	65%	71%	74%	79%	82%	68%	56%	60%	69%	68%
78.4%	78%	69%	68%	76%	77%	82%	78%	86%	88%	72%	88%	89%	77%	79%	73%	77%	77%	78%	80%	80%	74%
85.2%	87%	88%	81%	80%	77%	74%	87%	88%	90%	85%	90%	88%	93%	85%	84%	94%	88%	86%	79%	80%	86%
82.2%	78%	81%	80%	78%	85%	72%	85%	84%	87%	84%	86%	82%	87%	89%	80%	79%	84%	89%	82%	67%	87%
72.3%	71%	71%	74%	74%	72%	72%	77%	74%	77%	72%	78%	68%	74%	77%	70%	68%	69%	68%	71%	74%	68%
78.4%	78%	84%	79%	77%	77%	78%	85%	85%	84%	79%	84%	73%	84%	85%	76%	81%	81%	66%	71%	78%	62%
72.0%	73%	77%	71%	75%	70%	72%	73%	67%	75%	68%	82%	72%	69%	75%	61%	73%	67%	79%	78%	69%	66%
72.3%	77%	68%	70%	77%	75%	67%	69%	65%	72%	78%	72%	75%	75%	72%	78%	74%	70%	65%	73%	72%	74%
75.5%	85%	75%	71%	75%	80%	55%	72%	77%	77%	76%	65%	79%	81%	70%	78%	84%	81%	81%	73%	73%	77%
80.5%	91%	81%	80%	81%	94%	63%	83%	92%	91%	81%	80%	76%	83%	64%	94%	89%	81%	85%	67%	68%	67%
75.4%	88%	87%	88%	94%	75%	67%	74%	72%	72%	67%	72%	64%	66%	67%	75%	77%	69%	71%	75%	70%	93%
68.9%	69%	77%	71%	77%	89%	64%	62%	81%	67%	68%	74%	69%	74%	63%	65%	65%	61%	61%	68%	61%	61%
79.6%	78%	82%	82%	78%	78%	72%	81%	82%	83%	75%	83%	83%	81%	80%	74%	75%	84%	85%	79%	80%	76%
91.5%	88%	94%	88%	89%	86%	86%	97%	88%	98%	86%	88%	88%	88%	97%	93%	95%	97%	97%	100%	81%	98%
65.2%	69%	63%	69%	68%	71%	71%	61%	69%	59%	71%	69%	69%	69%	61%	58%	62%	60%	60%	58%	75%	58%
77.8%	92%	82%	79%	91%	86%	68%	82%	81%	85%	81%	81%	71%	68%	66%	88%	82%	76%	83%	66%	53%	73%
68.7%	73%	83%	67%	67%	47%	74%	65%	69%	65%	72%	56%	60%	76%	89%	63%	58%	65%	60%	86%	76%	71%
82.4%	95%	88%	91%	93%	83%	73%	84%	91%	78%	88%	77%	77%	84%	71%	90%	79%	80%	79%	66%	77%	86%
73.0%	75%	80%	73%	74%	62%	67%	79%	82%	75%	67%	75%	78%	73%	74%	74%	74%	71%	67%	68%	73%	73%
88.0%	94%	96%	95%	95%	89%	93%	94%	95%	94%	90%	89%	72%	89%	81%	97%	92%	72%	77%	86%	64%	93%
82.7%	88%	82%	91%	87%	82%	71%	89%	93%	88%	76%	77%	90%	87%	79%	92%	91%	90%	70%	73%	75%	65%
84.3%	84%	82%	88%	87%	91%	91%	80%	88%	78%	91%	88%	88%	88%	80%	77%	82%	79%	79%	77%	95%	77%
78.5%	84%	84%	80%	83%	81%	78%	84%	85%	87%	89%	84%	64%	80%	72%	87%	89%	72%	27%	80%	77%	81%
90.4%	97%	92%	93%	93%	98%	89%	96%	97%	93%	96%	78%	87%	97%	86%	87%	95%	83%	73%	92%	88%	89%
78.5%	66%	86%	86%	75%	68%	82%	77%	57%	70%	77%	96%	83%	78%	86%	81%	79%	75%	97%	86%	72%	72%

Model Similarity Dendrogram

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