	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 78.1%	3rd 79.3%	2nd 80.6%	1st 80.7%	15th 73.1%	17th 73.0%	7th 77.5%	14th 74.4%	13th 75.7%	10th 77.0%	9th 77.0%	16th 73.0%	8th 77.2%	12th 76.2%	6th 77.5%	5th 78.0%	18th 72.8%	20th 70.5%	11th 76.6%	19th 72.2%	21st 70.4%
88.4%	94%	89%	93%	96%	81%	74%	94%	92%	88%	94%	92%	86%	87%	90%	94%	87%	91%	79%	94%	80%	82%
71.8%	68%	66%	74%	79%	37%	75%	65%	72%	63%	63%	83%	92%	69%	76%	86%	80%	70%	83%	61%	76%	70%
85.8%		83%	95%	88%	76%	89%	80%	85%	80%	95%	98%	69%	84%	89%	87%	86%	91%	93%	77%	79%	92%
78.8%	80%	78%	80%	86%	77%	80%	77%	79%	82%	72%	80%	70%	82%	78%	82%	82%	82%	70%	85%	77%	75%
85.6%	89%	91%	87%	89%	78%	79%	91%	89%	79%	83%	82%	95%	86%	83%	95%	89%	79%	77%	89%	75%	92%
82.5%	75%	81%	75%	78%	69%	87%	88%	84%	92%	83%	81%	70%	89%	90%	80%	81%	83%	96%	88%	90%	72%
85.8%	85%	85%	82%	84%	82%	90%	85%	87%	84%	88%	85%	88%	88%	92%	90%	87%	83%	88%	72%	91%	86%
75.0%	88%	75%	81%	80%	73%	50%	82%	72%	78%	83%	80%	74%	77%	77%	74%	76%	64%	64%	68%	81%	78%
74.5%	65%	80%	73%	73%	89%	73%	90%	80%	93%	77%	78%	71%	78%	78%	60%	65%	64%	66%	78%	75%	58%
71.0%	72%	80%	73%	72%	70%	70%	67%	63%	70%	72%	70%	70%	72%	70%	76%	69%	60%	79%	70%	70%	77%
78.6%		85%	91%	89%	88%	91%	91%	72%	74%	57%	86%	85%	69%	80%	72%	66%	60%	48%	93%	88%	86%
76.7%	81%	88%	86%	86%	82%	82%	78%	71%	77%	68%	74%	82%	64%	70%	77%	74%	66%	79%	82%	71%	73%
66.3%	56%	68%	77%	80%	76%	78%	62%	57%	65%	69%	84%	66%	74%	78%	53%	65%	53%	47%	79%	53%	53%
79.7%	86%	83%	87%	87%	85%	66%	86%	80%	90%	83%	77%	58%	85%	70%	81%	83%	80%	85%	84%		57%
81.1%	83%	85%	87%	91%	87%	77%	84%	81%	81%	85%	86%	75%	82%	77%	77%	86%	82%	79%	78%	73%	68%
82.2%	86%	81%	86%	83%	70%	85%	80%	82%	82%	87%	82%	90%	82%	93%	89%	92%	74%	69%	87%	72%	75%
77.5%		89%	86%	81%	82%	77%	81%	68%	78%	79%	82%	81%	69%	76%	87%	86%	74%	51%	82%	83%	57%
71.7%	78%	81%	77%	82%	69%	40%	68%	78%	68%	76%	69%	69%	70%	68%	78%	76%	82%	63%	69%	76%	68%
61.7%	64%	49%	64%	54%	56%	45%	62%	69%	62%	72%	59%	48%	62%	68%	75%	83%	69%	49%	53%	66%	66%
81.5%	91%	94%	93%	94%	87%	69%	90%	76%	71%	88%	77%	71%	87%	78%	85%	77%	71%	76%	77%	71%	88%
73.0%	70%	74%	82%	84%	75%	70%	68%	64%	81%	76%	76%	73%	76%	77%	69%	80%	65%	69%	66%	76%	62%
77.4%	78%	80%	85%	81%	81%	70%	81%	77%	80%	81%	76%	73%	81%	83%	80%	80%	75%	74%	71%	77%	61%
81.7%	83%	94%	83%	79%	76%	89%	93%	80%	76%	87%	94%	48%	80%	75%	79%	91%	84%	86%	83%	79%	76%
69.9%	72%	77%	81%	81%	70%	80%	69%	62%	73%	73%	81%	57%	72%	78%	73%	69%	62%	46%	72%	59%	60%
67.4%	66%	66%	69%	68%	69%	66%	72%	64%	64%	69%	68%	69%	64%	60%	63%	68%	72%	71%	78%	65%	65%
68.1%	68%	74%	72%	72%	64%	68%	65%	60%	69%	72%	68%	64%	69%	78%	72%	78%	65%	57%	73%	74%	49%
75.6%	88%	82%	76%	81%	71%	51%	74%	92%	73%	79%	51%	66%	88%	61%	87%	83%	77%	82%	76%	78%	71%
84.8%	94%	96%	96%	94%	70%	73%	94%	96%	85%	93%	88%	86%	89%	75%	87%	92%	81%	71%	77%	82%	62%
73.4%	78%	85%	90%	83%	77%	64%	74%	63%	72%	70%	67%	68%	72%	67%	75%	74%	72%	67%	67%	67%	89%
68.9%	78%	68%	71%	73%	81%	65%	58%	72%	71%	69%	69%	60%	70%	69%	73%	69%	61%	67%	73%	71%	59%
73.7%	79%	78%	77%	78%	78%	68%	80%	79%	75%	75%	75%	74%	80%	61%	81%	78%	68%	77%	71%	71%	45%
60.8%		66%	53%	60%	72%	59%	68%	64%	68%	53%	51%	79%	64%	60%	64%	62%	57%	56%	71%	32%	57%
61.5%		58%	70%	63%	52%	64%	55%	60%	55%	70%	73%	46%	59%	64%	62%	61%	66%	67%	53%	66%	66%
76.5%	82%	72%	80%	88%	87%	72%	75%	75%	75%	75%	74%	71%	71%	72%	78%	80%	84%	78%	68%	71%	78%
69.7%	77%	77%	77%	86%	33%	77%	52%	59%	65%	67%	66%	67%	75%	76%	75%	70%	77%	51%	81%		87%
68.5%	69%	73%	76%	75%	39%	79%	73%	73%	59%	70%	71%	82%	63%	69%	60%	63%	74%	55%	80%	67%	69%
74.5%	71%	73%	82%	76%	80%	90%	68%	60%	77%	71%	82%	70%	82%	92%	68%	80%	56%	64%	80%	77%	65%
78.8%		85%	88%	98%	95%	92%	91%	85%	95%	94%	74%	75%	93%	78%	76%	75%	59%	59%	84%	40%	40%
79.0%	79%	82%	86%	80%	71%	78%	85%	76%	83%	80%	80%	86%	83%	73%	84%	87%	70%	76%	77%	75%	69%
91.5%		100%	87%	94%	93%	93%	97%	98%	97%	87%	84%	87%	98%	94%	95%	97%	91%	89%	94%	63%	93%
76.0%	80%	82%	83%	78%	54%	71%	78%	74%	67%	78%	81%	76%	81%	75%	80%	76%	82%	75%	81%	74%	70%
76.9%	81%	80%	74%	74%	75%	53%	87%	70%	72%	75%	80%	82%	76%	82%	80%	78%	81%	76%	75%	80%	84%
73.2%		77%	80%	74%	68%	71%	74%	58%	65%	73%	78%	71%	78%	77%	75%	75%	72%	76%	75%	68%	79%

Model Similarity Dendrogram

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