	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 69.2%	2nd 69.7%	21st 63.2%	19th 65.5%	5th 68.9%	18th 65.7%	10th 68.2%	13th 67.2%	9th 68.4%	11th 68.0%	6th 68.7%	8th 68.5%	4th 69.0%	16th 66.5%	7th 68.6%	1st 70.1%	12th 67.6%	20th 64.0%	14th 66.7%	15th 66.7%	17th 66.2%
73.9%	65%	75%	75%	67%	69%	64%	79%	79%	79%	90%	77%	69%	71%	83%	79%	74%	73%	67%	71%	66%	80%
72.3%	65%	68%	71%	70%	76%	70%	64%	60%	68%	82%	80%	80%	74%	80%	74%	70%	82%	66%	72%	73%	74%
75.7%	75%	75%	0%	75%	75%	84%	67%	90%	63%	90%	80%	80%	80%	84%	80%	87%	84%	71%	71%	80%	98%
75.9%	70%	84%	73%	75%	81%	73%	73%	70%	78%	75%	81%	75%	75%	70%	70%	88%	78%	74%	81%	75%	75%
88.2%	95%	90%	87%	87%	90%	81%	87%	95%	96%	94%	85%	94%	87%	87%	84%	90%	94%	85%	86%	85%	74%
91.0%	97%	95%	92%	84%	84%	97%	95%	77%	95%	90%	95%	91%	97%	88%	97%	97%	89%	84%	97%	85%	85%
76.6%	73%	73%	80%	77%	73%	77%	83%	70%	66%	74%	73%	72%	73%	72%	86%	85%	79%	79%	73%	75%	95%
75.9%	76%	84%	73%	81%	86%	71%	76%	69%	72%	59%	77%	86%	86%	86%	71%	71%	70%	69%	89%	82%	60%
75.0%	87%	72%	65%	73%	70%	53%	67%	77%	70%	87%	82%	82%	87%	72%	68%	81%	77%	75%	71%	73%	87%
76.0%	77%	79%	77%	77%	77%	84%	76%	67%	67%	77%	77%	75%	77%	74%	83%	77%	71%	77%	74%		77%
57.0%	60%	61%	60%	60%	44%	64%	64%	60%	60%	46%	64%	60%	53%	43%	52%	60%	47%	46%	66%	60%	67%
65.4%	68%	65%	68%	68%	68%	77%	62%	68%	66%	60%	61%	67%	60%	68%	60%	64%	70%	58%	71%	61%	64%
63.0%	62%	64%	65%	67%	69%	76%	58%	56%	65%	64%	60%	50%	70%	67%	70%	64%	65%	50%	66%	64%	50%
73.2%	83%	79%	71%	72%	87%	69%	84%	79%	66%	55%	76%	77%	80%	70%	78%	76%	63%	57%	87%	67%	61%
50.1%	53%	54%	52%	50%	48%	48%	53%	46%	53%	43%	48%	51%	54%	49%	47%	49%	54%	50%	49%	53%	49%
76.3%	78%	79%	78%	83%	72%	69%	78%	84%	76%	76%	82%	70%	82%	78%	72%	82%	74%	75%	71%	67%	77%
54.8%	50%	57%	52%	65%	57%	57%	50%	58%	55%	60%	60%	44%	50%	55%	62%	51%	57%	50%	57%	48%	56%
63.5%	71%	62%	66%	66%	57%	43%	63%	69%	69%	70%	57%	57%	63%	63%	66%	61%	63%	70%	58%	69%	71%
54.2%	74%	41%	68%	72%	77%	41%	57%	53%	68%	50%	53%	37%	50%	39%	58%	78%	42%	46%	41%	53%	40%
69.6%	68%	62%	67%	67%	73%	75%	69%	66%	66%	79%	69%	73%	75%	69%	69%	67%	75%	71%	63%		70%
64.6%	69%	72%	76%	70%	62%	56%	65%	60%	63%	74%	67%	63%	66%	62%	70%	68%	61%	54%	51%	57%	71%
79.8%	75%	80%	84%	73%	94%	70%	94%	72%	89%	69%	76%	89%	83%	80%	75%	92%	80%	66%	60%	83%	92%
69.0%	77%	68%	77%	77%	67%	63%	72%	67%	65%	65%	65%	72%	65%	59%	70%	70%	70%	72%	65%	72%	72%
64.1%	63%	66%	63%	63%	67%	67%	58%	61%	64%	63%	66%	53%	68%	69%	67%	68%	69%	67%	69%	67%	48%
51.2%	50%	51%	50%	51%	54%	45%	50%	48%	52%	49%	54%	54%	55%	54%	52%	52%	52%	52%	54%		46%
56.0%	46%	63%	57%	61%	64%	64%	59%	48%	59%	59%	59%	59%	52%	61%	43%	54%	52%	53%	63%	59%	40%
69.0%	78%	71%	69%	69%	61%	48%	65%	78%	73%	60%	49%	70%	72%	59%	77%	75%	85%	79%	70%	72%	70%
61.0%	63%	66%	65%	63%	62%	53%	70%	64%	51%	70%	68%	62%	62%	51%	57%	68%	69%	53%	53%	46%	66%
72.6%	77%	73%	77%	77%	82%	75%	71%	68%	72%	68%	75%	72%	68%	59%	77%	76%	71%	72%	68%	68%	78%
72.8%	70%	71%	74%	79%	86%	53%	70%	75%	75%	74%	71%	94%	72%	72%	70%	67%	76%	64%	67%	78%	70%
56.6%	66%	60%	59%	61%	59%	57%	58%	59%	57%	51%	56%	61%	53%	56%	59%	61%	55%	58%	58%	55%	29%
54.6%	63%	65%	0%	0%	63%	54%	71%	49%	75%	49%	58%	58%	58%	54%	67%	63%	54%	58%	63%	67%	58%
52.0%	55%	53%	0%	0%	55%	63%	48%	67%	44%	67%	59%	59%	59%	63%	59%	59%	63%	59%	55%	55%	51%
47.5%	53%	51%	49%	54%	62%	43%	49%	57%	47%	47%	51%	43%	34%	43%	46%	46%	46%	47%	36%	46%	48%
47.4%	46%	57%	49%	53%	22%	60%	32%	51%	57%	49%	46%	57%	53%	53%	45%	43%	49%	46%	57%	41%	30%
76.0%	76%	82%	77%	84%	70%	75%	78%	80%	72%	84%	77%	79%	77%	72%	71%	76%	71%	75%	66%		78%
66.0%	63%	67%	66%	65%	59%	68%	68%	60%	69%	66%	68%	68%	73%	69%	65%	64%	71%	52%	69%	69%	67%
82.3%	82%	92%	87%	82%	87%	86%	78%	85%	82%	78%	97%	74%	96%	79%	86%	85%	62%	66%	81%	77%	87%
71.6%	74%	75%	79%	79%	69%	65%	76%	73%	75%	69%	74%	73%	69%	69%	75%	75%	67%	73%	61%	69%	65%
71.1%	87%	82%	0%	0%	82%	73%	91%	68%	95%	68%	78%	78%	78%	73%	78%	77%	73%	78%	82%	87%	66%
66.1%	66%	68%	73%	68%	68%	77%	65%	68%	63%	75%	68%	67%	70%	62%	63%	64%	62%	61%	62%	56%	63%
74.0%	72%	79%	77%	77%	72%	69%	72%	74%	77%	82%	73%	78%	74%	73%	77%	75%	74%	63%	78%	74%	63%
67.3%	59%	67%	70%	75%	64%	66%	66%	66%	66%	66%	64%	71%	64%	71%	73%	65%	66%	64%	67%	67%	77%

Model Similarity Dendrogram

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