	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 83.2%	17th 75.7%	1st 83.7%	3rd 82.9%	8th 79.9%	21st 72.4%	12th 79.3%	6th 81.0%	11th 79.5%	5th 81.3%	10th 79.7%	13th 77.3%	9th 79.8%	14th 76.5%	7th 80.4%	4th 81.7%	15th 76.1%	18th 75.6%	16th 76.1%	19th 74.7%	20th 72.5%
80.7%		88%	85%	91%	79%	68%	79%	87%	74%	77%	81%	90%	84%	78%	82%	78%	81%	82%	86%	72%	73%
76.7%		67%	82%	82%	68%	85%	66%	69%	64%	77%	88%	93%	84%	92%	81%	82%	66%	52%	90%	72%	74%
69.5%		0%	76%	64%	77%	73%	68%	82%	64%	81%	83%	76%	73%	76%	64%	74%	74%	72%	65%	74%	74%
89.0%	93%	82%	92%	88%	92%	80%	90%	95%	96%	90%	93%	87%	93%	82%	92%	92%	85%	87%	88%	88%	83%
90.2%		90%	90%	92%	80%	82%	87%	94%	94%	96%	96%	94%	96%	95%	93%	93%	93%	89%	82%	86%	83%
77.6%		83%	79%	83%	85%	75%	79%	88%	82%	82%	78%	65%	77%	68%	75%	78%	77%	75%	76%	62%	86%
89.4%	91%	92%	90%	92%	86%	92%	85%	94%	93%	92%	84%	89%	88%	90%	90%	95%	93%	92%	80%	95%	74%
76.4%		77%	74%	89%	92%	46%	78%	81%	76%	83%	70%	80%	74%	73%	88%	83%	79%	72%	64%	81%	68%
81.6%		84%	86%	80%	90%	66%	76%	76%	77%	93%	87%	84%	80%	77%	83%	87%	87%	93%	76%	75%	75%
85.9%	87%	87%	87%	93%	87%	95%	81%	82%	87%	87%	80%	87%	87%	87%	80%	85%	74%	74%	87%	95%	94%
81.3%		91%	90%	87%	90%	89%	88%	84%	86%	75%	89%	80%	69%	70%	74%	80%	59%	70%	85%	86%	85%
86.3%	95%	89%	90%	96%	94%	74%	86%	90%	91%	80%	86%	96%	73%	86%	80%	86%	76%	76%	90%		92%
80.3%		87%	85%	87%	88%	82%	81%	82%	77%	83%	92%	78%	90%	90%	72%	74%	68%	68%	86%	68%	68%
79.3%		82%	84%	82%	86%	73%	84%	85%	82%	82%	82%	64%	82%	66%	82%	85%	74%	83%	84%	74%	69%
86.4%		91%	92%	86%	94%	86%	91%	90%	90%	88%	91%	88%	92%	87%	86%	93%	82%	78%	74%	91%	58%
76.7%		84%	88%	88%	82%	63%	76%	82%	74%	80%	68%	76%	79%	78%	79%	84%	68%	83%	78%	63%	61%
61.1%		69%	72%	72%	62%	53%	65%	54%	70%	64%	57%	46%	49%	53%	70%	67%	55%	54%	67%	57%	65%
67.0%		67%	78%	85%	75%	41%	59%	74%	65%	66%	55%	68%	66%	59%	70%	66%	65%	73%	72%	60%	76%
62.8%	60%	52%	62%	56%	74%	46%	66%	70%	65%	71%	55%	46%	79%	61%	65%	77%	80%	46%	47%	84%	57%
82.3%	86%	87%	88%	87%	84%	77%	86%	77%	76%	88%	77%	78%	89%	75%	87%	89%	78%	77%	78%	78%	86%
85.2%		93%	93%	86%	97%	75%	94%	90%	94%	87%	91%	94%	97%	80%	85%	84%	69%	80%	78%	68%	68%
85.7%		88%	91%	86%	93%	62%	96%	94%	92%	84%	78%	91%	88%	85%	91%	91%	90%	89%	70%	83%	72%
76.0%	72%	83%	81%	75%	81%	87%	81%	78%	75%	77%	82%	78%	76%	82%	69%	71%	71%	65%	78%	69%	65%
85.5%		92%	93%	83%	93%	92%	80%	88%	88%	90%	90%	80%	89%	90%	83%	91%	79%	68%	84%	79%	79%
79.5%		83%	85%	80%	81%	76%	85%	80%	82%	82%	89%	66%	81%	68%	81%	82%	77%	88%	82%	74%	68%
71.8%		75%	75%	71%	74%	66%	70%	68%	75%	73%	71%	75%	74%	84%	67%	75%	66%	75%	75%	76%	51%
77.2%		82%	87%	86%	79%	54%	78%	79%	80%	78%	66%	79%	85%	73%	82%	81%	77%	74%	75%	77%	72%
77.5%		84%	76%	88%	77%	53%	89%	89%	83%	77%	71%	75%	78%	63%	93%	84%	82%	83%	54%	73%	78%
72.8%	87%	89%	90%	86%	82%	60%	71%	74%	67%	60%	70%	59%	61%	62%	83%	73%	61%	59%	74%	78%	83%
76.3%		83%	82%	92%	84%	64%	62%	83%	83%	77%	74%	63%	72%	70%	83%	77%	70%	86%	78%	79%	64%
84.7%		92%	93%	83%	89%	85%	84%	86%	85%	90%	94%	83%	84%	82%	86%	92%	72%	82%	75%	84%	72%
69.5%		0%	72%	85%	71%	75%	81%	66%	85%	67%	66%	72%	75%	72%	75%	74%	74%	77%	83%	46%	75%
62.9%		0%	69%	57%	70%	66%	61%	75%	57%	74%	75%	69%	66%	69%	67%	67%	67%	65%	58%	60%	67%
80.1%	86%	77%	86%	89%	61%	74%	77%	84%	81%	82%	75%	76%	78%	72%	83%	88%	86%	84%	76%		86%
64.9%	77%	80%	70%	70%	35%	62%	58%	55%	53%	61%	55%	69%	61%	65%	75%	62%	77%	61%	81%	59%	76%
77.8%		80%	88%	89%	62%	72%	83%	92%	82%	85%	84%	72%	82%	68%	77%	79%	84%	71%	66%	79%	62%
87.1%		91%	91%	85%	92%	84%	91%	79%	92%	94%	95%	88%	92%	87%	88%	97%	88%	86%	85%	82%	56%
85.5%		92%	94%	92%	82%	94%	90%	93%	95%	96%	98%	75%	94%	85%	87%	89%	85%	67%	83%	71%	48%
77.3%		81%	85%	84%	75%	66%	85%	86%	79%	85%	73%	77%	81%	61%	85%	81%	77%	79%	60%	73%	74%
84.8%		0%	93%	80%	95%	91%	85%	100%	81%	99%	100%	93%	90%	93%	80%	91%	92%	89%	82%	78%
80.0%		89%	82%	82%	67%	72%	87%	86%	83%	86%	88%	74%	77%	79%	85%	81%	78%	70%	74%	80%	80%
76.2%	81%	81%	79%	79%	75%	63%	77%	76%	76%	81%	74%	77%	76%	79%	79%	78%	74%	71%	73%	74%	78%
72.1%		89%	76%	76%	55%	76%	73%	47%	68%	74%	77%	74%	72%	76%	79%	79%	64%	85%	72%	61%	69%

Model Similarity Dendrogram

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