	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	7th 65.0%	8th 64.5%	1st 66.9%	3rd 66.4%	19th 59.0%	17th 61.3%	14th 62.2%	13th 62.3%	15th 61.7%	4th 66.0%	10th 64.2%	20th 58.9%	9th 64.2%	6th 65.2%	2nd 66.4%	5th 65.5%	16th 61.5%	21st 58.1%	11th 63.4%	12th 63.1%	17th 61.3%
70.2%	75%	66%	74%	75%	75%	61%	72%	75%	59%	90%	64%	60%	71%	72%	67%	69%	71%	54%	76%	72%	77%
52.3%	48%	46%	57%	60%	18%	54%	50%	50%	38%	63%	59%	56%	59%	56%	56%	59%	52%	50%	56%	53%	59%
50.8%	51%	50%	63%	44%	44%	55%	51%	56%	44%	51%	63%	48%	44%	59%	51%	51%	55%	48%	51%	44%	44%
64.1%	50%	69%	62%	51%	58%	68%	66%	66%	62%	66%	68%	58%	66%	66%	62%	66%	63%	66%	84%	67%	62%
74.3%	66%	77%	66%	66%	75%	65%	66%	87%	82%	77%	77%	65%	83%	78%	66%	72%	86%	71%	66%	95%	75%
72.3%	67%	66%	64%	67%	73%	73%	77%	72%	81%	72%	73%	81%	77%	77%	67%	73%	77%	73%	70%	72%	67%
67.7%	68%	75%	74%	74%	58%	66%	67%	67%	75%	70%	58%	75%	64%	63%	83%	66%	68%	60%	64%	71%	56%
49.5%	54%	54%	54%	54%	27%	33%	51%	49%	48%	65%	51%	48%	51%	51%	59%	58%	46%	37%	43%	48%	58%
65.4%	75%	66%	53%	53%	54%	41%	54%	64%	67%	75%	64%	63%	75%	75%	72%	70%	77%	68%	60%	73%	75%
58.0%	55%	55%	55%	55%	58%	57%	64%	60%	58%	60%	58%	58%	58%	58%	61%	58%	53%	60%	58%	61%	59%
54.6%	58%	63%	58%	58%	41%	64%	58%	67%	59%	51%	51%	64%	36%	59%	57%	51%	49%	44%	64%	59%	36%
59.0%	58%	67%	62%	55%	55%	65%	57%	65%	58%	46%	57%	68%	46%	65%	64%	54%	50%	58%	62%	73%	55%
58.4%	67%	61%	75%	75%	58%	72%	62%	51%	65%	63%	74%	58%	65%	74%	48%	61%	33%	47%	51%	33%	33%
57.0%	55%	55%	57%	64%	64%	51%	51%	45%	56%	56%	63%	61%	55%	63%	58%	60%	55%	56%	58%	54%	59%
61.8%	74%	59%	57%	68%	63%	64%	54%	42%	49%	63%	74%	41%	58%	74%	67%	67%	58%	51%	70%	70%	74%
65.5%	64%	61%	70%	70%	56%	61%	75%	64%	58%	86%	71%	47%	80%	76%	67%	67%	52%	41%	67%	78%	64%
74.9%	80%	82%	96%	85%	85%	63%	74%	46%	74%	70%	86%	63%	74%	74%	82%	82%	77%	58%	83%	77%	62%
63.8%	69%	58%	66%	74%	65%	45%	53%	69%	67%	52%	55%	87%	71%	60%	68%	67%	71%	45%	54%	70%	74%
50.6%	57%	39%	57%	42%	51%	42%	57%	60%	57%	67%	54%	25%	57%	57%	63%	65%	58%	39%	32%	44%	39%
63.9%	57%	65%	58%	58%	58%	69%	55%	64%	64%	63%	62%	71%	67%	64%	58%	67%	71%	61%	67%	71%	71%
50.3%	59%	57%	58%	55%	24%	43%	55%	53%	55%	64%	45%	45%	45%	47%	53%	54%	49%	51%	44%	54%	47%
63.1%	67%	66%	77%	77%	58%	71%	62%	48%	51%	64%	74%	51%	67%	66%	58%	51%	63%	51%	70%	67%	66%
53.4%	50%	56%	56%	43%	69%	70%	64%	69%	56%	56%	43%	35%	66%	72%	43%	40%	47%	56%	61%	35%	35%
57.2%	74%	61%	69%	74%	64%	70%	62%	47%	71%	61%	74%	47%	61%	64%	54%	63%	32%	32%	57%	32%	32%
58.9%	64%	61%	65%	67%	54%	58%	62%	59%	51%	51%	58%	58%	54%	52%	64%	62%	62%	47%	62%	68%	58%
54.4%	60%	55%	58%	63%	43%	51%	52%	56%	54%	60%	56%	38%	61%	55%	60%	60%	49%	53%	56%	52%	51%
65.0%	71%	71%	63%	74%	67%	54%	57%	61%	58%	87%	55%	47%	75%	61%	76%	69%	67%	58%	64%	67%	64%
67.8%	71%	77%	75%	74%	74%	55%	71%	69%	62%	67%	62%	59%	62%	59%	76%	75%	78%	77%	51%	56%	74%
61.2%	59%	76%	78%	78%	66%	64%	61%	61%	61%	43%	53%	58%	43%	46%	78%	76%	40%	46%	78%	73%	48%
74.9%	70%	75%	75%	92%	92%	57%	54%	73%	70%	64%	85%	80%	68%	69%	80%	82%	73%	72%	92%	80%	69%
59.5%	64%	57%	62%	75%	67%	66%	55%	41%	47%	57%	64%	47%	64%	66%	66%	63%	61%	50%	55%	53%	69%
86.3%	87%	88%	73%	87%	95%	82%	87%	81%	95%	87%	73%	91%	95%	78%	87%	84%	82%	78%	87%	100%	95%
51.5%	51%	50%	63%	44%	44%	55%	51%	56%	44%	51%	63%	48%	44%	59%	51%	54%	55%	59%	51%	44%	44%
69.1%	67%	77%	76%	60%	43%	71%	70%	75%	71%	75%	67%	71%	71%	70%	71%	60%	70%	67%	72%	74%	74%
59.6%	63%	55%	63%	63%	37%	61%	56%	63%	58%	60%	58%	70%	63%	56%	72%	62%	56%	63%	63%	68%	42%
71.4%	75%	74%	77%	84%	52%	73%	71%	70%	63%	77%	69%	64%	84%	64%	71%	76%	71%	75%	65%	63%	81%
73.8%	79%	83%	75%	84%	73%	72%	62%	57%	60%	77%	79%	60%	73%	74%	84%	83%	74%	76%	76%	64%	84%
82.7%	85%	81%	97%	90%	77%	92%	84%	90%	87%	84%	77%	64%	92%	85%	88%	88%	73%	59%	92%	68%	84%
58.0%	65%	52%	56%	63%	53%	56%	59%	61%	54%	77%	51%	54%	59%	51%	66%	62%	62%	60%	44%	54%	59%
71.7%	71%	70%	84%	63%	63%	75%	71%	77%	63%	71%	84%	67%	63%	80%	77%	74%	75%	80%	71%	63%	63%
73.6%	75%	69%	71%	70%	71%	59%	74%	76%	82%	86%	64%	74%	70%	67%	79%	77%	61%	82%	66%	96%	77%
59.3%	58%	67%	58%	56%	58%	51%	58%	60%	56%	50%	69%	56%	65%	73%	66%	62%	64%	58%	58%	44%	58%
61.1%	64%	62%	70%	70%	55%	62%	64%	58%	64%	64%	56%	53%	60%	70%	60%	56%	60%	60%	56%	55%	64%

Model Similarity Dendrogram

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