	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 71.0%	10th 66.3%	7th 66.9%	4th 68.0%	12th 65.2%	19th 61.2%	3rd 68.8%	8th 66.4%	6th 67.7%	9th 66.3%	15th 63.7%	20th 60.8%	11th 65.8%	21st 60.4%	2nd 69.1%	5th 67.8%	13th 64.7%	18th 62.2%	15th 63.7%	14th 64.6%	17th 63.6%
74.3%		90%	75%	78%	68%	88%	83%	75%	90%	68%	68%	65%	68%	51%	78%	68%	66%	63%	85%	75%	83%
60.0%		59%	64%	70%	37%	69%	69%	64%	50%	75%	69%	44%	64%	70%	74%	59%	25%	62%	74%	52%	50%
43.5%		38%	41%	41%	37%	34%	100%	44%	41%	52%	41%	34%	41%	41%	41%	34%	41%	41%	34%	41%	52%
68.2%	79%	55%	68%	67%	74%	70%	71%	70%	63%	77%	70%	70%	71%	41%	74%	77%	63%	66%	67%	70%
64.6%		71%	71%	71%	54%	54%	68%	64%	71%	71%	54%	54%	71%	54%	81%	87%	71%	54%	54%	54%	64%
80.7%		71%	71%	71%	71%	60%	87%	68%	87%	100%	87%	82%	87%	87%	91%	81%	80%	84%	100%	87%	62%
77.9%	82%	66%	68%	82%	76%	65%	79%	87%	82%	79%	81%	79%	79%	65%	82%	79%	82%	80%	81%	81%	80%
63.8%		58%	61%	61%	80%	58%	59%	74%	67%	65%	54%	56%	57%	47%	60%	72%	73%	78%	58%	58%	80%
79.0%		72%	72%	82%	91%	84%	82%	82%	91%	79%	70%	70%	79%	70%	78%	89%	72%	83%	82%	80%	72%
69.4%	70%	70%	74%	87%	58%	65%	65%	62%	79%	70%	70%	70%	74%	70%	74%	74%	65%	46%	70%	70%	74%
45.3%		60%	69%	60%	54%	46%	48%	54%	48%	39%	48%	54%	31%	39%	40%	37%	32%	22%	54%	62%	9%
73.6%	78%	75%	74%	74%	73%	90%	71%	70%	89%	62%	69%	70%	71%	74%	84%	75%	72%	60%	70%	70%	74%
80.7%	75%	91%	76%	76%	88%	88%	91%	88%	100%	71%	68%	68%	88%	68%	91%	87%	87%	76%	68%	68%
84.0%	89%	78%	78%	74%	78%	83%	78%	87%	100%	83%	83%	81%	83%	89%	89%	100%	74%	83%	83%	83%	87%
68.8%		84%	77%	77%	54%	57%	77%	77%	69%	77%	84%	54%	69%	54%	77%	76%	69%	54%	69%	68%	54%
72.9%		68%	77%	78%	79%	76%	76%	73%	68%	77%	68%	78%	78%	79%	78%	78%	71%	32%	68%	82%	74%
62.2%		69%	91%	74%	56%	58%	63%	40%	58%	69%	76%	76%	49%	60%	66%	63%	50%	37%	63%	63%	63%
57.3%		56%	56%	56%	75%	49%	49%	62%	63%	56%	51%	51%	51%	36%	68%	50%	70%	77%	51%	63%	56%
37.5%	43%	20%	43%	37%	78%	9%	31%	22%	43%	50%	20%	10%	43%	8%	61%	61%	43%	50%	22%	47%	47%
57.3%	65%	62%	64%	64%	56%	50%	64%	52%	60%	56%	54%	39%	60%	61%	69%	69%	60%	47%	58%	39%	55%
62.4%		67%	63%	63%	60%	67%	62%	60%	60%	58%	65%	59%	62%	59%	66%	70%	58%	70%	56%	59%	64%
78.7%	82%	85%	73%	82%	79%	78%	82%	87%	78%	78%	87%	59%	78%	88%	78%	73%	82%	67%	88%	78%	70%
59.5%	70%	62%	56%	64%	59%	74%	58%	60%	54%	60%	60%	55%	63%	65%	60%	51%	48%	54%	65%	58%	53%
67.8%		66%	75%	63%	68%	68%	75%	63%	63%	68%	68%	68%	68%	68%	63%	63%	63%	68%	68%	68%	81%
77.5%	75%	70%	70%	65%	66%	83%	70%	83%	83%	83%	83%	83%	83%	83%	75%	75%	75%	82%	83%	83%	75%
62.0%		71%	71%	63%	63%	71%	71%	65%	65%	65%	71%	65%	52%	44%	52%	63%	52%	47%	75%	52%	61%
59.6%		45%	68%	68%	60%	52%	54%	68%	68%	61%	46%	47%	68%	48%	68%	59%	65%	63%	60%	68%	56%
40.3%		41%	41%	54%	70%	19%	34%	46%	46%	34%	25%	41%	41%	25%	50%	53%	34%	44%	25%	41%	41%
70.5%	69%	100%	88%	88%	63%	63%	75%	75%	69%	63%	76%	55%	53%	66%	76%	73%	56%	61%	76%	74%	61%
75.9%		68%	77%	77%	73%	63%	77%	78%	68%	76%	78%	78%	90%	78%	77%	79%	82%	91%	65%	71%	71%
51.5%	47%	47%	50%	50%	43%	49%	54%	54%	47%	47%	52%	52%	47%	60%	47%	52%	65%	54%	52%	56%	56%
81.8%		92%	69%	69%	92%	92%	92%	85%	92%	60%	92%	92%	92%	85%	60%	60%	77%	92%	92%	92%	60%
44.2%		38%	41%	41%	37%	34%	100%	44%	41%	52%	41%	34%	41%	41%	52%	38%	41%	41%	34%	41%	52%
59.9%	76%	56%	68%	82%	74%	51%	49%	61%	59%	51%	39%	75%	39%	54%	74%	74%	82%	51%	41%	42%
60.8%	65%	75%	65%	70%	41%	68%	51%	70%	54%	62%	39%	70%	70%	70%	60%	58%	69%	65%	41%	54%	60%
59.7%	58%	59%	62%	63%	55%	44%	61%	63%	58%	75%	76%	61%	68%	39%	63%	56%	58%	64%	44%	56%	70%
65.3%		67%	66%	66%	68%	45%	68%	79%	73%	68%	52%	52%	68%	43%	79%	80%	70%	65%	67%	52%	79%
59.4%		65%	65%	61%	56%	54%	65%	50%	54%	69%	54%	40%	57%	54%	69%	69%	65%	71%	54%	54%	62%
53.5%		57%	50%	53%	42%	39%	57%	59%	48%	61%	61%	39%	61%	57%	58%	69%	42%	54%	45%	50%	69%
86.3%		92%	80%	85%	92%	92%	85%	93%	92%	70%	92%	92%	92%	92%	70%	70%	92%	92%	92%	92%	70%
56.5%		55%	56%	63%	63%	29%	50%	53%	69%	54%	61%	47%	63%	51%	58%	58%	78%	59%	51%	56%	55%
83.0%	84%	84%	83%	83%	82%	74%	90%	84%	84%	83%	75%	83%	83%	89%	86%	83%	90%	63%	81%	100%	79%
69.0%		75%	68%	69%	60%	68%	68%	61%	68%	78%	63%	63%	75%	75%	75%	75%	70%	63%	75%	69%	63%

Model Similarity Dendrogram

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