	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	1st 80.2%	4th 78.1%	5th 78.0%	2nd 78.7%	15th 74.2%	19th 72.5%	8th 77.3%	11th 76.1%	12th 75.9%	10th 76.6%	6th 78.0%	13th 74.7%	9th 77.0%	16th 74.2%	7th 77.7%	3rd 78.3%	17th 74.0%	21st 70.0%	14th 74.6%	20th 70.8%	18th 73.5%
77.2%	79%	79%	73%	72%	85%	73%	73%	71%	75%	69%	85%	85%	77%	79%	75%	80%	72%	90%	87%	72%	71%
84.5%	87%	84%	88%	85%	77%	85%	89%	87%	77%	91%	90%	84%	88%	85%	79%	89%	80%	80%	86%	84%	79%
69.5%	68%	66%	72%	71%	60%	75%	62%	74%	64%	75%	68%	68%	60%	70%	65%	66%	62%	77%	65%	86%	86%
84.4%	93%	86%	84%	90%	81%	73%	93%	91%	85%	93%	84%	84%	85%	77%	86%	82%	80%	74%	78%	89%	85%
91.0%	88%	92%	94%	93%	92%	93%	94%	95%	90%	93%	92%	89%	96%	97%	89%	90%	87%	87%	94%	70%	97%
93.3%	97%	93%	93%	93%	92%	97%	95%	93%	90%	94%	97%	89%	88%	89%	92%	97%	96%	95%	97%	91%	92%
85.8%	93%	86%	91%	91%	88%	84%	89%	85%	86%	79%	90%	90%	89%	88%	79%	88%	89%	75%	88%	76%	77%
82.4%	89%	80%	82%	82%	79%	60%	86%	87%	86%	84%	90%	85%	85%	85%	87%	84%	87%	71%	79%	73%	90%
78.9%	82%	76%	69%	77%	71%	69%	77%	82%	80%	82%	78%	83%	78%	78%	78%	76%	87%	88%	77%	96%	73%
81.1%	89%	76%	83%	82%	90%	74%	80%	80%	82%	91%	88%	92%	91%	73%	77%	80%	77%	74%	70%	78%	77%
66.3%	71%	76%	79%	84%	54%	78%	73%	79%	62%	60%	74%	62%	53%	52%	61%	57%	67%	35%	83%	73%	60%
84.1%	86%	86%	83%	91%	83%	90%	75%	85%	82%	88%	84%	88%	95%	81%	86%	81%	82%	71%	85%	75%	89%
75.6%	89%	85%	88%	76%	69%	76%	82%	82%	81%	78%	78%	64%	78%	78%	86%	81%	75%	77%	75%	10%	79%
72.1%	79%	80%	75%	72%	79%	75%	79%	69%	67%	75%	75%	63%	73%	75%	77%	79%	61%	54%	77%	67%	63%
68.0%	67%	73%	69%	69%	64%	63%	72%	72%	67%	65%	68%	68%	68%	70%	71%	70%	67%	66%	64%	67%	67%
73.9%	78%	74%	77%	80%	76%	74%	72%	70%	74%	75%	73%	76%	72%	78%	81%	73%	66%	69%	73%	70%	70%
63.8%	72%	85%	75%	64%	66%	61%	69%	54%	62%	61%	61%	52%	60%	63%	77%	72%	58%	42%	65%	62%	59%
70.1%	84%	68%	69%	78%	64%	52%	64%	78%	71%	65%	68%	72%	77%	63%	73%	73%	79%	65%	65%	72%	72%
59.9%	69%	46%	73%	63%	65%	43%	62%	56%	56%	73%	62%	51%	69%	55%	72%	73%	50%	45%	43%	67%	65%
66.8%	70%	60%	57%	69%	70%	68%	63%	69%	68%	71%	68%	68%	72%	60%	63%	68%	70%	64%	65%	70%	69%
81.3%	86%	85%	85%	88%	80%	72%	87%	77%	85%	77%	84%	79%	82%	78%	84%	87%	84%	77%	68%	77%	85%
75.0%	84%	83%	78%	81%	72%	65%	81%	78%	76%	76%	78%	71%	77%	71%	83%	81%	71%	69%	65%	70%	66%
79.7%	80%	87%	87%	88%	69%	80%	74%	76%	79%	80%	84%	73%	75%	72%	85%	88%	81%	73%	95%	78%	70%
74.3%	81%	72%	77%	80%	78%	71%	79%	78%	86%	71%	77%	68%	81%	76%	78%	72%	74%	59%	67%	71%	64%
70.5%	72%	79%	71%	69%	79%	73%	75%	64%	69%	67%	79%	76%	67%	73%	66%	70%	57%	68%	73%	74%	59%
62.1%	63%	67%	63%	69%	63%	69%	60%	51%	60%	64%	62%	63%	60%	66%	64%	70%	61%	64%	65%	58%	43%
76.9%	79%	78%	75%	74%	77%	55%	78%	80%	82%	71%	71%	80%	82%	74%	80%	82%	75%	78%	84%	79%	80%
72.0%	77%	80%	72%	76%	86%	52%	73%	78%	79%	78%	67%	67%	67%	60%	80%	81%	75%	77%	61%	71%	56%
71.0%	79%	77%	75%	79%	73%	69%	73%	61%	67%	69%	67%	73%	66%	65%	76%	74%	70%	73%	71%	72%	63%
81.0%	84%	92%	77%	78%	84%	76%	75%	89%	81%	70%	90%	79%	87%	80%	79%	81%	93%	73%	85%	76%	72%
73.7%	78%	75%	77%	78%	78%	74%	75%	74%	79%	75%	80%	71%	73%	73%	80%	80%	72%	63%	73%	68%	52%
66.3%	66%	68%	62%	63%	75%	59%	73%	60%	71%	60%	66%	66%	75%	65%	73%	68%	73%	58%	70%	49%	73%
78.9%	83%	77%	83%	82%	70%	86%	72%	85%	74%	86%	79%	79%	70%	80%	72%	76%	72%	87%	75%	72%	97%
73.0%	68%	73%	69%	66%	61%	77%	73%	70%	72%	73%	76%	76%	81%	73%	73%	71%	76%	70%	74%	68%	92%
74.6%	84%	75%	79%	79%	59%	83%	73%	88%	70%	81%	80%	72%	80%	82%	73%	70%	63%	77%	64%	65%	69%
77.3%	83%	81%	83%	82%	82%	67%	81%	84%	83%	82%	81%	72%	79%	70%	85%	88%	74%	66%	69%	71%	61%
86.0%	92%	94%	89%	89%	71%	79%	92%	81%	87%	89%	87%	84%	91%	87%	91%	95%	84%	74%	77%	90%	83%
79.6%	90%	77%	90%	98%	87%	85%	97%	78%	87%	88%	92%	63%	87%	70%	82%	79%	53%	57%	74%	53%	85%
62.9%	69%	65%	73%	73%	64%	63%	64%	60%	63%	61%	63%	64%	60%	63%	66%	70%	61%	52%	63%	53%	51%
92.6%	93%	95%	89%	90%	98%	86%	100%	87%	98%	86%	93%	93%	98%	92%	97%	95%	100%	84%	97%	75%	98%
78.3%	88%	80%	86%	81%	44%	76%	76%	88%	73%	90%	83%	78%	78%	79%	78%	77%	79%	70%	73%	76%	91%
80.1%	82%	83%	83%	82%	82%	80%	88%	82%	79%	86%	72%	81%	81%	75%	81%	86%	81%	72%	81%	70%	75%
61.0%	58%	66%	59%	57%	55%	57%	58%	46%	59%	52%	70%	72%	58%	71%	63%	65%	60%	71%	66%	62%	56%

Model Similarity Dendrogram

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