	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	5th 78.8%	13th 76.4%	4th 78.9%	1st 80.3%	17th 74.3%	21st 71.4%	11th 76.5%	10th 77.0%	9th 78.0%	2nd 79.0%	12th 76.5%	20th 71.4%	7th 78.3%	18th 74.3%	2nd 79.0%	6th 78.3%	16th 75.5%	15th 75.7%	19th 73.7%	8th 78.2%	14th 76.0%
86.3%		87%	95%	95%	74%	94%	91%	89%	95%	82%	92%	74%	90%	63%	90%	95%	89%	73%	90%		81%
60.3%		60%	62%	61%	54%	68%	61%	57%	61%	69%	66%	50%	65%	49%	63%	55%	58%	59%	61%	65%	61%
79.5%		84%	72%	83%	55%	55%	91%	70%	68%	83%	91%	86%	91%	91%	84%	84%	83%	91%	55%	91%	83%
84.9%	94%	71%	79%	90%	81%	74%	91%	93%	84%	94%	90%	90%	90%	78%	82%	80%	74%	91%	85%	90%	82%
78.3%		75%	75%	80%	75%	75%	83%	83%	83%	83%	75%	75%	75%	75%	82%	87%	79%	75%	75%	75%	80%
84.3%		95%	94%	94%	92%	69%	83%	82%	87%	82%	79%	86%	82%	71%	90%	87%	82%	83%	78%	83%	86%
73.1%		74%	70%	76%	72%	64%	70%	74%	76%	70%	69%	69%	69%	69%	84%	78%	71%	83%	69%	81%	75%
76.7%		75%	76%	76%	80%	56%	71%	81%	76%	83%	71%	74%	75%	71%	86%	89%	83%	77%	72%	75%	87%
81.1%		68%	74%	74%	79%	68%	79%	81%	83%	84%	82%	88%	84%	84%	84%	92%	80%	91%	84%		82%
83.3%	90%	69%	78%	86%	90%	90%	79%	77%	79%	85%	88%	78%	90%	90%	78%	90%	78%	71%	90%	90%	83%
68.4%		74%	86%	82%	47%	74%	79%	87%	69%	60%	83%	69%	72%	57%	59%	69%	49%	44%	74%	91%	43%
68.7%	83%	72%	72%	77%	78%	69%	64%	69%	67%	63%	67%	69%	66%	64%	67%	72%	62%	60%	70%	63%	69%
88.6%		82%	80%	82%	80%	78%	82%	92%	91%	90%	95%	80%	95%	95%	87%	92%	100%	94%	95%	95%	87%
84.3%	90%	90%	77%	86%	85%	85%	81%	85%	89%	90%	85%	69%	93%	84%	80%	82%	78%	86%	85%	87%	83%
82.4%		89%	86%	86%	83%	86%	89%	83%	85%	89%	85%	75%	85%	72%	86%	78%	79%	80%	82%	75%	75%
79.5%		76%	84%	84%	74%	76%	84%	80%	82%	82%	78%	75%	80%	82%	83%	80%	75%	82%	68%	81%	83%
76.1%		83%	93%	84%	82%	73%	72%	61%	78%	76%	83%	79%	57%	72%	82%	86%	69%	55%	78%	76%	82%
60.8%		52%	62%	62%	63%	67%	60%	63%	56%	64%	64%	52%	64%	57%	66%	60%	69%	64%	49%	59%	63%
61.7%	69%	57%	72%	65%	57%	51%	65%	60%	64%	69%	56%	43%	65%	63%	69%	70%	59%	60%	53%		67%
68.1%	78%	59%	74%	71%	74%	69%	69%	73%	69%	73%	58%	61%	70%	69%	61%	61%	71%	74%	66%	72%	59%
77.0%		75%	81%	79%	76%	77%	74%	76%	74%	79%	75%	76%	79%	79%	76%	83%	78%	83%	74%	72%	75%
86.9%		90%	81%	90%	94%	90%	90%	84%	90%	95%	81%	70%	94%	83%	90%		90%	84%	84%	84%	88%
68.1%	66%	72%	72%	72%	71%	71%	68%	66%	65%	73%	71%	60%	72%	72%	71%	66%	62%	66%	68%	60%	66%
89.1%		73%	78%	81%	95%	89%	84%	87%	90%	94%	95%	95%	95%	95%	90%	82%	93%	90%	95%	87%	95%
80.5%		82%	76%	76%	84%	77%	78%	81%	91%	82%	75%	66%	85%	82%	78%	76%	82%	90%	85%	81%	84%
71.0%		81%	77%	77%	73%	61%	77%	73%	76%	76%	74%	69%	74%	61%	77%	64%	58%	67%	74%	66%	66%
67.8%		59%	69%	74%	78%	59%	64%	74%	70%	73%	60%	48%	69%	63%	77%	66%	77%	58%	65%	74%	80%
80.5%		87%	87%	87%	73%	61%	83%	95%	83%	78%	75%	78%	81%	66%	91%	86%	86%	82%	66%	79%	86%
72.7%	81%	92%	92%	85%	78%	69%	85%	68%	69%	66%	60%	67%	66%	60%	78%	73%	73%	59%	78%	60%	67%
74.5%		78%	76%	88%	84%	59%	74%	82%	72%	73%	70%	70%	74%	70%	85%	74%	79%	76%	74%	74%	59%
80.0%		79%	74%	79%	83%	68%	79%	77%	79%	79%	82%	86%	79%	86%	82%	83%	79%	86%	75%	83%	82%
57.0%		55%	60%	61%	61%	55%	64%	69%	64%	55%	55%	43%	55%	64%	55%	55%	55%	61%	43%	55%	55%
89.7%		96%	85%	85%	91%	91%	96%	81%	81%	96%	85%	90%	91%	91%	96%	96%	96%	91%	64%	96%	96%
71.8%	78%	68%	72%	85%	72%	66%	72%	69%	74%	72%	61%	61%	69%	76%	73%	76%	71%	76%	62%	83%	72%
65.6%	66%	71%	76%	69%	49%	52%	70%	76%	81%	61%	60%	34%	69%	63%	69%	76%	77%	62%	62%	73%	62%
71.8%		72%	72%	72%	60%	59%	81%	80%	75%	78%	77%	78%	78%	69%	74%	66%	67%	74%	67%		65%
85.3%		85%	91%	95%	86%	89%	10%	85%	90%	95%	93%	86%	89%	86%	90%	89%	84%	86%	87%	95%	94%
86.3%		90%	90%	90%	90%	87%	91%	80%	93%	93%	93%	75%	90%	75%	93%	90%	71%	89%	75%	85%	86%
82.7%		86%	86%	86%	73%	77%	86%	85%	84%	86%	82%	67%	85%	84%	85%	86%	85%	77%	84%	86%	85%
68.0%		79%	81%	79%	43%	43%	67%	59%	59%	67%	76%	76%	67%	76%	67%	67%	67%	76%	76%	67%	67%
71.8%		73%	75%	77%	72%	57%	80%	67%	78%	71%	78%	53%	78%	68%	72%	73%	75%	77%	68%	78%	67%
77.4%	72%	69%	83%	76%	69%	81%	85%	80%	83%	92%	76%	95%	80%	82%	70%	85%	68%	63%	78%	71%	67%
87.3%		80%	97%	94%	67%	90%	89%	75%	89%	94%	77%	86%	91%	89%	97%	91%	85%	87%	87%	91%	91%

Model Similarity Dendrogram

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