	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 74.7%	13th 71.0%	2nd 74.7%	3rd 74.2%	7th 72.6%	19th 66.9%	4th 73.7%	10th 71.8%	9th 72.0%	5th 73.4%	12th 71.6%	14th 68.9%	10th 71.8%	15th 67.9%	8th 72.5%	6th 72.7%	16th 67.7%	21st 64.6%	17th 67.1%	18th 67.0%	20th 66.9%
74.8%	75%	76%	77%	75%	64%	74%	78%	72%	75%	77%	76%	75%	77%	77%	75%	75%	73%	71%	79%	74%	75%
72.2%	73%	77%	75%	77%	66%	78%	73%	79%	64%	78%	75%	73%	74%	68%	66%	76%	66%	63%	74%	75%	67%
71.2%	81%	67%	81%	77%	67%	73%	70%	71%	67%	77%	77%	77%	70%	72%	67%	72%	64%	77%	63%	63%	62%
73.6%	80%	69%	76%	69%	71%	71%	76%	80%	80%	76%	76%	73%	80%	71%	73%	76%	70%	68%	58%	73%	80%
88.8%	95%	93%	90%	90%	87%	90%	90%	90%	87%	85%	91%	91%	87%	92%	87%	90%	96%	83%	91%	93%	67%
66.3%	66%	68%	66%	72%	71%	65%	63%	74%	66%	66%	73%	59%	66%	59%	66%	68%	59%	71%	63%	59%	73%
83.5%	91%	77%	89%	83%	87%	74%	85%	89%	87%	89%	88%	75%	79%	75%	93%	91%	89%	70%	80%	80%	83%
70.6%	85%	61%	75%	84%	64%	42%	71%	79%	69%	76%	73%	72%	69%	63%	78%	81%	74%	73%	61%	60%	72%
80.4%	71%	80%	82%	73%	83%	70%	79%	89%	83%	82%	85%	82%	87%	85%	75%	71%	83%	79%	87%	85%	78%
79.2%	75%	84%	78%	82%	80%	81%	79%	76%	81%	77%	77%	79%	80%	82%	85%	81%	73%	72%	82%	75%	84%
85.4%	98%	91%	92%	90%	79%	89%	94%	84%	94%	81%	84%	87%	81%	76%	88%	74%	70%	77%	98%		80%
77.2%	90%	79%	79%	77%	81%	80%	70%	80%	80%	75%	73%	79%	79%	75%	80%	81%	73%	51%	73%	82%	85%
77.2%	65%	83%	72%	68%	80%	87%	76%	69%	76%	89%	90%	60%	82%	81%	79%	79%	79%	81%	92%	83%	50%
65.5%	66%	72%	66%	66%	71%	56%	73%	68%	64%	62%	72%	78%	64%	78%	61%	63%	68%	52%	72%	51%	53%
71.4%	76%	76%	78%	81%	76%	67%	78%	72%	72%	76%	69%	71%	72%	70%	65%	72%	69%	62%	64%	66%	68%
66.6%	77%	65%	79%	69%	79%	51%	66%	73%	59%	76%	66%	59%	68%	60%	75%	69%	64%	55%	61%	63%	65%
63.3%	69%	73%	75%	75%	74%	53%	74%	46%	63%	60%	62%	53%	59%	60%	70%	74%	44%	52%	60%	67%	67%
61.7%	76%	56%	73%	75%	67%	46%	56%	73%	60%	70%	60%	52%	60%	53%	69%	65%	57%	55%	60%	53%	59%
45.4%	47%	35%	46%	42%	54%	32%	52%	36%	42%	47%	41%	56%	52%	28%	67%	63%	50%	37%	26%	54%	47%
82.8%	89%	75%	87%	88%	86%	82%	88%	74%	80%	88%	82%	74%	86%	73%	77%	81%	91%	85%	87%	90%	75%
82.5%	77%	91%	88%	74%	85%	74%	86%	69%	91%	90%	83%	82%	89%	84%	85%	84%	85%	79%	66%	85%	85%
75.8%	83%	78%	83%	83%	74%	68%	83%	72%	81%	78%	81%	70%	81%	72%	78%	82%	69%	64%	65%	69%	77%
64.1%	57%	57%	68%	65%	72%	72%	67%	61%	67%	60%	67%	57%	63%	70%	65%	64%	61%	63%	70%	65%	56%
77.8%	83%	81%	84%	76%	78%	79%	83%	76%	78%	83%	81%	72%	84%	78%	85%	81%	76%	63%	70%		64%
66.7%	65%	71%	68%	65%	68%	70%	73%	67%	67%	62%	69%	70%	67%	70%	66%	67%	65%	63%	68%	62%	58%
67.1%	69%	70%	66%	66%	75%	68%	65%	57%	67%	67%	68%	78%	63%	79%	68%	66%	67%	67%	70%	53%	61%
56.5%	61%	58%	60%	58%	59%	45%	55%	57%	57%	63%	54%	56%	57%	55%	58%	59%	54%	51%	54%	51%	64%
56.3%	66%	58%	61%	71%	85%	37%	58%	64%	68%	58%	54%	54%	52%	46%	66%	58%	42%	37%	38%	45%	64%
70.1%	80%	85%	81%	92%	74%	70%	80%	66%	63%	59%	80%	58%	67%	66%	61%	70%	61%	58%	72%	65%	65%
62.3%	73%	57%	68%	72%	80%	55%	60%	70%	66%	67%	62%	52%	64%	53%	64%	58%	54%	64%	56%	58%	55%
61.1%	65%	61%	70%	70%	65%	60%	67%	71%	65%	65%	54%	61%	66%	56%	60%	61%	58%	49%	52%	57%	51%
62.4%	62%	68%	53%	57%	68%	62%	64%	64%	68%	57%	57%	57%	64%	62%	64%	63%	71%	58%	71%	71%	50%
54.6%	55%	50%	63%	59%	50%	55%	53%	54%	50%	59%	59%	59%	53%	55%	50%	55%	50%	59%	47%	46%	66%
74.8%	78%	71%	78%	76%	83%	70%	85%	83%	76%	91%	76%	65%	68%	58%	79%	84%	79%	73%	62%	71%	64%
68.6%	69%	66%	75%	69%	41%	70%	73%	73%	72%	78%	73%	74%	76%	67%	76%	70%	74%	58%	53%	64%	70%
68.7%	79%	73%	74%	74%	72%	58%	72%	75%	71%	75%	70%	68%	72%	59%	70%	69%	59%	65%	52%	72%	63%
75.0%	74%	69%	83%	92%	52%	70%	90%	84%	82%	76%	66%	91%	79%	72%	76%	72%	67%	59%	69%	83%	70%
80.9%	86%	84%	93%	86%	77%	93%	89%	91%	85%	85%	82%	72%	85%	70%	93%	90%	77%	66%	90%	52%	52%
54.0%	67%	52%	59%	64%	57%	49%	57%	65%	57%	64%	52%	58%	58%	54%	54%	44%	37%	36%	42%	47%	60%
94.9%	98%	94%	91%	95%	94%	100%	98%	98%	94%	95%	95%	95%	98%	100%	94%	99%	91%	96%	90%	90%	87%
63.2%	69%	54%	63%	64%	74%	53%	71%	68%	75%	67%	63%	47%	66%	49%	68%	71%	67%	61%	49%	62%	66%
80.2%	81%	79%	77%	80%	89%	74%	92%	81%	83%	88%	71%	73%	80%	76%	76%	84%	78%	78%	84%	82%	78%
65.0%	72%	67%	70%	70%	61%	65%	59%	47%	64%	64%	73%	68%	63%	70%	67%	72%	59%	77%	66%	52%	59%

Model Similarity Dendrogram

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