	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 4.1 Fast
Score	3rd 71.8%	1st 72.3%	2nd 72.1%	4th 71.6%	19th 65.0%	15th 68.3%	12th 69.0%	14th 68.6%	10th 69.1%	7th 70.3%	6th 70.6%	16th 66.7%	8th 69.9%	11th 69.1%	9th 69.8%	5th 70.7%	18th 65.3%	17th 66.5%	13th 68.8%	20th 63.7%	21st 63.0%
74.9%	81%	79%	78%	81%	63%	70%	73%	81%	79%	87%	73%	87%	79%	74%	79%	78%	69%	62%	82%	59%	59%
65.2%	71%	70%	67%	67%	37%	66%	69%	68%	73%	59%	68%	68%	75%	68%	68%	63%	70%	58%	67%	55%	63%
66.9%	75%	66%	75%	69%	59%	72%	62%	75%	59%	69%	72%	69%	62%	69%	62%	69%	65%	69%	62%	62%	62%
88.5%	89%	85%	89%	93%	69%	85%	100%	81%	89%	100%	100%	80%	80%	93%	100%	100%	100%	88%	78%	80%	80%
83.0%	81%	88%	75%	81%	83%	74%	75%	87%	80%	87%	90%	81%	87%	81%	85%	91%	95%	94%	75%	86%	67%
63.6%	62%	66%	62%	62%	74%	70%	57%	80%	64%	63%	71%	62%	63%	57%	58%	58%	57%	63%	63%	55%	68%
76.3%	78%	72%	78%	80%	74%	81%	74%	78%	78%	76%	74%	79%	78%	82%	74%	78%	66%	82%	68%	78%	74%
68.4%	70%	71%	71%	77%	66%	58%	66%	75%	70%	68%	71%	71%	71%	77%	71%	73%	76%	71%	71%	44%	48%
81.4%	80%	84%	81%	81%	87%	62%	74%	87%	74%	95%	87%	78%	95%	78%	89%	89%	87%	76%	74%	76%	76%
73.5%	80%	71%	64%	71%	80%	80%	69%	61%	80%	68%	80%	80%	70%	80%	71%	74%	70%	80%	80%	64%	71%
70.7%	74%	82%	82%	74%	52%	86%	82%	66%	68%	68%	61%	86%	61%	82%	68%	68%	52%	51%	72%	82%	67%
65.4%	65%	60%	73%	65%	58%	65%	74%	72%	73%	63%	64%	55%	74%	68%	65%	65%	63%	67%	65%	65%	55%
57.2%	47%	67%	71%	71%	65%	77%	57%	41%	61%	53%	68%	51%	58%	72%	48%	53%	41%	41%	77%	41%	41%
64.2%	62%	70%	64%	71%	64%	54%	64%	58%	62%	61%	66%	59%	66%	59%	71%	69%	66%	62%	69%	61%	71%
75.5%	82%	76%	74%	74%	68%	81%	66%	65%	66%	77%	78%	66%	77%	87%	83%	82%	68%	69%	78%	74%	95%
60.9%	78%	71%	75%	64%	51%	56%	61%	68%	64%	66%	45%	69%	64%	56%	60%	68%	45%	46%	61%	65%	46%
59.1%	66%	82%	68%	62%	80%	51%	63%	50%	63%	50%	54%	43%	63%	60%	60%	66%	57%	41%	52%	63%	48%
69.2%	87%	80%	74%	87%	74%	42%	67%	74%	72%	72%	62%	69%	66%	51%	77%	71%	78%	82%	62%	48%	59%
52.4%	55%	40%	50%	48%	61%	36%	57%	58%	53%	57%	51%	51%	58%	47%	64%	64%	40%	51%	40%	68%	51%
86.0%	88%	87%	93%	84%	87%	83%	90%	87%	89%	93%	89%	76%	93%	90%	85%	92%	76%	69%	86%	76%	93%
66.5%	66%	65%	69%	70%	64%	66%	70%	60%	70%	62%	70%	73%	70%	69%	64%	65%	58%	71%	80%		48%
72.3%	78%	82%	87%	77%	65%	70%	75%	75%	74%	71%	70%	78%	75%	77%	80%	73%	62%	74%	70%	55%	50%
73.1%	68%	78%	78%	71%	79%	78%	79%	72%	78%	79%	82%	51%	79%	79%	68%	69%	64%	77%	84%		49%
62.5%	59%	74%	68%	68%	55%	72%	56%	56%	61%	61%	65%	54%	68%	68%	58%	68%	55%	55%	81%	55%	55%
68.5%	66%	76%	78%	76%	68%	60%	77%	61%	69%	71%	78%	62%	64%	65%	74%	65%	50%	72%	75%	66%	65%
59.0%	51%	65%	57%	52%	44%	74%	60%	50%	49%	63%	67%	63%	59%	80%	56%	58%	55%	50%	60%	66%	60%
62.6%	59%	56%	59%	59%	50%	81%	62%	57%	71%	71%	86%	69%	69%	84%	48%	59%	48%	56%	69%	54%	48%
59.9%	64%	63%	64%	64%	96%	43%	64%	63%	64%	62%	64%	50%	50%	37%	70%	64%	54%	62%	48%	50%	61%
63.6%	71%	66%	70%	80%	70%	55%	71%	64%	65%	56%	63%	49%	56%	56%	70%	63%	52%	52%	56%	80%	71%
62.1%	78%	70%	69%	69%	62%	60%	50%	75%	67%	62%	64%	53%	62%	44%	64%	69%	56%	76%	64%	47%	43%
63.4%	60%	76%	65%	60%	60%	60%	63%	62%	63%	68%	71%	63%	68%	68%	60%	63%	59%	59%	64%	52%	68%
62.3%	60%	63%	54%	69%	69%	57%	66%	54%	69%	60%	57%	60%	66%	60%	66%	64%	57%	65%	66%	60%	66%
77.0%	91%	77%	86%	69%	69%	82%	73%	86%	69%	79%	82%	79%	73%	79%	73%	75%	82%	73%	73%	73%	73%
75.4%	80%	71%	80%	78%	62%	78%	72%	78%	78%	71%	76%	76%	76%	76%	80%	67%	80%	80%	68%	76%	80%
57.3%	65%	78%	73%	71%	48%	63%	48%	48%	48%	51%	48%	52%	51%	52%	65%	56%	55%	54%	64%	65%	49%
59.2%	61%	61%	61%	61%	25%	67%	56%	61%	56%	55%	64%	62%	61%	58%	55%	57%	60%	56%	62%	70%	74%
72.8%	74%	76%	69%	69%	69%	75%	72%	61%	72%	77%	74%	72%	74%	82%	69%	71%	64%	71%	74%	83%	81%
76.1%	87%	65%	81%	75%	75%	82%	87%	87%	87%	87%	69%	62%	87%	68%	81%	81%	81%	66%	75%	62%	54%
58.0%	71%	62%	59%	59%	27%	54%	64%	62%	62%	71%	59%	59%	62%	45%	63%	61%	64%	54%	52%	62%	45%
77.9%	86%	77%	86%	79%	69%	82%	73%	86%	69%	79%	82%	79%	73%	79%	79%	79%	75%	79%	73%	73%	79%
74.0%	78%	78%	73%	89%	55%	76%	89%	85%	77%	95%	77%	67%	78%	58%	83%	77%	82%	80%	67%	24%	67%
74.7%	73%	80%	73%	73%	78%	72%	73%	74%	80%	80%	66%	76%	73%	85%	74%	77%	73%	71%	73%	71%	73%
73.5%	72%	83%	79%	79%	85%	79%	68%	62%	58%	60%	79%	79%	72%	72%	65%	86%	79%	85%	79%	65%	58%

Model Similarity Dendrogram

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