	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	4th 79.5%	14th 76.2%	9th 78.0%	3rd 79.6%	16th 75.2%	20th 71.8%	18th 74.6%	7th 78.8%	8th 78.2%	6th 78.9%	15th 75.7%	19th 73.5%	11th 77.4%	21st 71.1%	1st 81.0%	2nd 80.1%	12th 76.7%	13th 76.4%	17th 75.1%	10th 77.7%	5th 79.0%
82.6%	83%	91%	79%	82%	68%	84%	79%	83%	82%	83%	77%	80%	83%	81%	80%	86%	89%	87%	86%	85%	86%
78.7%	79%	81%	79%	84%	63%	70%	88%	79%	74%	83%	83%	73%	80%	78%	88%	86%	79%	69%	72%	84%	80%
61.2%	62%	62%	62%	65%	62%	89%	10%	65%	62%	62%	62%	62%	62%	37%	62%	62%	62%	89%	62%	62%	62%
87.1%	90%	77%	84%	92%	88%	92%	91%	83%	85%	86%	93%	92%	94%	81%	82%	79%	85%	87%	92%	92%	85%
80.6%	82%	77%	77%	82%	72%	72%	96%	95%	88%	92%	72%	72%	90%	72%	87%	92%	76%	74%	72%	72%
90.4%	90%	90%	92%	90%	90%	74%	92%	90%	92%	92%	89%	89%	87%	87%	95%	100%	92%	95%	100%	89%	84%
86.2%	88%	76%	89%	92%	86%	84%	79%	90%	87%	87%	82%	88%	83%	80%	89%	87%	93%	93%	83%	84%	90%
75.5%	81%	73%	75%	81%	64%	63%	68%	83%	72%	82%	64%	77%	75%	69%	85%	82%	76%	81%	75%		85%
77.7%	82%	60%	70%	70%	88%	69%	75%	79%	80%	79%	78%	73%	84%	72%	81%	85%	87%	91%	70%		81%
87.3%	92%	88%	79%	82%	92%	92%	85%	82%	78%	91%	76%	95%	92%	92%	86%	91%	80%	86%	92%	92%	91%
65.0%	68%	79%	84%	77%	66%	66%	68%	77%	60%	63%	67%	75%	66%	56%	69%	62%	47%	46%	60%	65%	44%
78.7%	93%	91%	81%	93%	88%	10%	79%	92%	80%	79%	84%	88%	86%	69%	82%	83%	79%	58%	84%	76%
90.0%	91%	90%	94%	94%	95%	78%	100%	88%	95%	95%	91%	91%	95%	91%	95%	90%	81%	76%	91%	91%	79%
84.0%	84%	88%	88%	82%	95%	79%	78%	77%	78%	85%	95%	73%	84%	81%	91%	91%	84%	72%	95%	81%	84%
71.3%	75%	71%	70%	73%	69%	77%	72%	78%	71%	71%	70%	67%	72%	66%	66%	68%	76%	69%	67%	77%
78.8%	78%	79%	84%	82%	74%	79%	81%	80%	78%	81%	81%	67%	81%	78%	79%	79%	76%	76%	83%		81%
75.4%	64%	83%	83%	83%	65%	73%	64%	59%	79%	83%	83%	77%	65%	63%	75%	83%	79%	79%	67%	82%	95%
74.0%	79%	68%	74%	75%	74%	72%	69%	70%	74%	71%	71%	75%	71%	60%	84%	80%	85%	86%	71%		72%
68.9%	82%	70%	70%	70%	65%	56%	74%	68%	73%	74%	62%	57%	70%	53%	74%	73%	70%	68%	64%	78%	76%
68.9%	74%	59%	66%	69%	69%	66%	77%	67%	73%	72%	67%	64%	70%	68%	74%	64%	74%	68%	69%	72%	65%
85.0%	92%	76%	83%	83%	86%	89%	78%	92%	87%	83%	92%	86%	84%	78%	91%	92%	94%	88%	76%	73%	82%
83.2%	90%	89%	87%	85%	83%	85%	88%	85%	79%	90%	75%	84%	84%	92%	86%	80%	78%	69%	74%	77%	88%
76.3%	82%	78%	78%	79%	51%	70%	71%	80%	79%	66%	86%	73%	63%	74%	83%	84%	68%	83%	86%	96%	73%
85.2%	87%	68%	82%	82%	84%	91%	87%	85%	81%	88%	88%	91%	91%	91%	82%	88%	84%	80%	91%	91%	78%
84.8%	82%	94%	90%	82%	82%	83%	79%	84%	82%	85%	82%	71%	82%	79%	88%	82%	82%	95%	95%	95%	87%
65.3%	74%	75%	68%	73%	66%	58%	66%	56%	65%	70%	75%	49%	63%	52%	66%	68%	62%	58%	68%	66%	74%
71.2%	71%	55%	66%	77%	75%	79%	66%	73%	75%	64%	59%	49%	79%	74%	78%	69%	76%	81%	76%	72%	82%
72.7%	80%	73%	78%	78%	84%	53%	71%	80%	79%	80%	70%	59%	70%	59%	81%	79%	65%	74%	62%	67%	84%
70.5%	71%	79%	66%	74%	69%	61%	73%	65%	66%	73%	73%	73%	73%	53%	74%	72%	72%	73%	73%	73%	74%
77.9%	91%	75%	81%	81%	65%	70%	80%	86%	90%	75%	70%	73%	79%	76%	86%	83%	85%	81%	73%	61%	75%
75.6%	72%	75%	75%	79%	83%	74%	76%	78%	79%	80%	74%	74%	75%	74%	73%	77%	76%	77%	67%	76%	73%
55.1%	53%	53%	60%	50%	73%	46%	10%	69%	69%	53%	46%	73%	53%	46%	53%	53%	53%	73%	46%	73%	53%
74.9%	74%	74%	72%	76%	89%	89%	76%	76%	72%	74%	72%	72%	72%	72%	74%	74%	74%	72%	72%	72%	74%
72.2%	71%	73%	72%	68%	68%	72%	74%	74%	78%	75%	77%	71%	74%	74%	72%	72%	73%	73%	63%	68%	74%
75.5%	84%	80%	84%	79%	57%	75%	57%	73%	74%	69%	71%	78%	80%	73%	92%	84%	68%	71%	84%	71%	81%
74.1%	80%	67%	77%	88%	83%	52%	70%	78%	81%	82%	81%	52%	72%	62%	83%	86%	79%	73%	64%	69%	78%
82.6%	90%	79%	87%	87%	87%	82%	81%	91%	83%	87%	74%	74%	91%	69%	92%	91%	78%	74%	79%	74%	85%
78.9%	84%	78%	82%	87%	87%	72%	88%	78%	87%	84%	85%	54%	82%	72%	88%	79%	62%	74%	72%	78%	84%
70.0%	70%	70%	68%	73%	55%	68%	70%	67%	72%	67%	65%	93%	67%	64%	74%	70%	76%	72%	68%	68%	73%
78.4%	72%	73%	72%	89%	73%	72%	72%	96%	98%	89%	72%	62%	62%	72%	89%	89%	89%	72%	72%	73%	89%
79.9%	83%	80%	93%	87%	69%	59%	92%	90%	82%	94%	75%	52%	87%	59%	87%	86%	81%	81%	61%	92%	88%
81.5%	81%	82%	78%	84%	80%	75%	88%	84%	82%	86%	74%	94%	80%	83%	86%	84%	77%	70%	78%	89%	77%
71.2%	66%	79%	74%	64%	51%	69%	68%	62%	63%	68%	71%	69%	74%	76%		79%	75%	72%	74%	74%	96%

Model Similarity Dendrogram

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