	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	6th 80.0%	7th 78.8%	3rd 80.8%	1st 81.5%	13th 76.9%	19th 74.9%	10th 77.2%	14th 76.8%	9th 78.0%	5th 80.0%	17th 75.9%	21st 74.3%	8th 78.3%	18th 75.1%	2nd 81.2%	4th 80.1%	11th 77.1%	15th 76.7%	20th 74.4%	12th 77.0%	16th 76.5%
85.9%		85%	87%	86%	89%	91%	88%	85%	91%	84%	85%	80%	87%	83%	87%	87%	82%	84%	90%		81%
74.9%		79%	79%	82%	54%	83%	82%	76%	71%	68%	90%	61%	78%	91%	62%	70%	68%	87%	78%	75%	65%
74.2%		73%	70%	74%	82%	82%	73%	61%	62%	73%	82%	97%	69%	82%	73%	73%	73%	82%	47%	82%	73%
83.0%	86%	87%	81%	85%	79%	86%	84%	82%	89%	86%	89%	79%	85%	71%	88%	88%	84%	82%	74%	84%	74%
88.8%		88%	91%	91%	88%	88%	91%	91%	88%	92%	88%	88%	88%	88%	93%	87%	84%	88%	88%	88%	88%
77.1%		81%	80%	79%	81%	84%	78%	85%	75%	76%	74%	79%	75%	76%	79%	74%	75%	79%	70%	67%	75%
81.1%		79%	84%	84%	87%	73%	79%	85%	89%	83%	76%	74%	84%	85%	82%	86%	85%	84%	76%	89%	58%
61.2%		63%	69%	62%	63%	43%	55%	62%	60%	67%	53%	58%	62%	60%	66%	66%	65%	67%	53%	63%	66%
75.3%		77%	75%	75%	47%	59%	72%	75%	75%	82%	75%	72%	78%	75%	84%	86%	80%	83%	71%	77%	87%
79.0%	79%	87%	84%	82%	79%	87%	78%	66%	81%	83%	70%	84%	81%	79%	83%	74%	64%	78%	79%	76%	84%
80.2%		88%	90%	82%	59%	93%	87%	83%	86%	80%	81%	84%	72%	74%	85%	84%	78%	71%	84%	82%	61%
78.9%	86%	84%	86%	86%	82%	65%	81%	84%	79%	83%	74%	83%	78%	69%	87%	84%	67%	66%	79%	74%	80%
80.2%		79%	84%	84%	75%	81%	81%	84%	85%	83%	75%	69%	85%	75%	82%	84%	80%	78%	75%	84%	81%
85.8%	86%	85%	90%	90%	86%	79%	90%	90%	92%	87%	90%	73%	89%	78%	90%	90%	86%	79%	86%	80%	86%
82.2%		82%	86%	86%	88%	88%	70%	88%	84%	86%	81%	75%	88%	88%	74%	72%	78%	81%	86%	81%	81%
79.8%		84%	82%	82%	83%	73%	73%	75%	80%	85%	74%	73%	80%	77%	78%	75%	85%	77%	89%	87%	84%
69.9%		78%	80%	84%	70%	65%	60%	51%	63%	73%	71%	65%	54%	60%	77%	76%	71%	67%	69%	77%	88%
77.0%		75%	79%	78%	81%	79%	73%	75%	73%	82%	72%	72%	79%	70%	84%	81%	76%	80%	74%	81%	77%
53.1%	50%	46%	46%	46%	74%	53%	54%	57%	56%	57%	50%	37%	50%	53%	74%	64%	58%	47%	40%	54%	50%
83.0%	89%	86%	88%	87%	89%	80%	90%	86%	87%	79%	81%	81%	86%	87%	88%	86%	74%	71%	70%	77%	81%
82.9%		75%	93%	90%	84%	74%	73%	77%	81%	88%	80%	81%	90%	81%	88%	87%	90%	80%	78%	81%	86%
85.3%	89%	82%	89%	91%	89%	76%	85%	82%	75%	90%	68%	91%	92%	82%	89%	81%	91%	86%	83%	88%	92%
76.2%	73%	77%	82%	80%	67%	71%	79%	75%	76%	79%	82%	71%	73%	66%	82%	77%	76%	80%	82%		76%
75.0%		63%	78%	78%	75%	82%	83%	78%	78%	78%	78%	75%	78%	73%	78%	79%	78%	76%	79%	76%	37%
82.8%		81%	81%	84%	87%	85%	83%	86%	86%	84%	83%	76%	85%	84%	85%	82%	83%	85%	85%	80%	70%
77.6%		84%	77%	83%	84%	77%	80%	75%	82%	81%	75%	74%	72%	77%	79%	84%	74%	71%	77%	76%	71%
81.7%		85%	80%	82%	88%	86%	81%	82%	85%	80%	75%	76%	87%	77%	79%	84%	79%	73%	90%	88%	77%
71.7%		69%	78%	75%	88%	54%	77%	79%	81%	73%	66%	44%	73%	66%	77%	81%	75%	75%	57%	65%	80%
78.1%	85%	87%	89%	89%	84%	76%	80%	74%	74%	76%	79%	71%	70%	69%	82%	80%	71%	71%	72%		82%
78.5%		82%	83%	85%	76%	70%	73%	85%	80%	76%	72%	70%	83%	70%	87%	78%	81%	89%	80%	86%	65%
77.1%	78%	80%	75%	77%	66%	75%	77%	83%	76%	72%	81%	80%	74%	80%	79%	78%	78%	78%	75%	80%
52.1%		47%	53%	53%	47%	47%	63%	59%	71%	53%	56%	47%	47%	47%	53%	53%	53%	47%	47%	47%	53%
73.7%		73%	70%	74%	82%	82%	73%	61%	62%	73%	82%	97%	69%	82%	73%	73%	73%	82%	47%	73%	73%
75.4%	78%	68%	78%	80%	81%	74%	70%	81%	76%	78%	70%	70%	73%	76%	81%	80%	79%	76%	68%	70%	76%
62.7%	75%	84%	76%	85%	65%	50%	46%	47%	52%	56%	43%	59%	61%	49%	72%	68%	55%	73%	69%	49%	82%
80.8%		79%	83%	84%	66%	68%	84%	82%	80%	89%	86%	83%	88%	77%	80%	80%	84%	79%	79%		85%
86.4%		85%	93%	97%	89%	79%	85%	89%	89%	90%	80%	80%	97%	87%	90%	89%	85%	74%	90%	89%	71%
86.6%		88%	85%	90%	65%	93%	86%	80%	92%	92%	86%	85%	87%	88%	89%	89%	80%	80%	88%	93%	95%
75.3%		82%	86%	86%	81%	70%	72%	79%	75%	85%	70%	67%	87%	67%	74%	74%	67%	79%	62%	64%	80%
82.5%		82%	82%	82%	82%	82%	81%	85%	63%	95%	63%	82%	82%	82%	95%	95%	95%	63%	82%	82%	95%
77.6%		70%	75%	76%	77%	70%	77%	78%	80%	87%	88%	60%	88%	61%	86%	88%	79%	76%	62%	85%	89%
79.5%	86%	85%	84%	85%	79%	59%	82%	82%	82%	84%	80%	83%	76%	81%	80%	84%	84%	79%	78%	66%	70%
88.7%		95%	95%	95%	69%	87%	90%	64%	94%	92%	88%	88%	86%	87%	97%	93%	94%	93%	91%	88%	88%

Model Similarity Dendrogram

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