	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 74.1%	4th 69.9%	18th 64.2%	8th 69.0%	14th 66.2%	16th 65.4%	9th 68.4%	11th 68.0%	12th 67.8%	5th 69.9%	6th 69.8%	19th 63.8%	7th 69.4%	10th 68.4%	2nd 70.7%	3rd 70.6%	15th 66.0%	20th 63.4%	13th 67.3%	17th 64.5%	21st 62.6%
61.4%	69%	64%	66%	67%	59%	47%	53%	63%	64%	55%	64%	64%	61%	59%	59%	69%	66%	61%	63%	55%
64.1%	62%	64%	63%	55%	40%	76%	63%	58%	61%	55%	76%	77%	76%	80%	66%	55%	64%	54%	77%	66%	58%
88.1%	100%	98%	0%	100%	78%	92%	92%	92%	91%	100%	95%	85%	100%	95%	91%	100%	95%	95%	89%	81%	81%
75.9%	76%	70%	80%	70%	76%	70%	70%	76%	70%	76%	89%	70%	76%	70%	89%	89%	76%	80%	70%	76%
65.7%	80%	59%	80%	80%	61%	80%	80%	69%	69%	61%	61%	69%	61%	59%	58%	50%	48%	43%	72%	64%	76%
68.7%	77%	70%	69%	69%	72%	62%	70%	77%	70%	70%	70%	53%	68%	66%	69%	66%	79%	79%	62%	56%	69%
81.0%	84%	87%	87%	75%	76%	72%	86%	90%	100%	77%	84%	75%	75%	87%	77%	75%	88%	84%	72%	75%	75%
58.0%	69%	63%	66%	70%	62%	45%	61%	51%	49%	77%	58%	54%	58%	54%	49%	62%	56%	42%	47%	63%	63%
70.2%	69%	69%	77%	69%	73%	47%	61%	77%	61%	69%	77%	69%	69%	68%	76%	69%	68%	73%	77%	72%	84%
65.2%	72%	66%	63%	67%	76%	53%	72%	63%	68%	72%	72%	76%	72%	60%	67%	63%	55%	60%	53%	42%	77%
58.5%	72%	60%	60%	60%	44%	72%	60%	60%	60%	49%	60%	53%	56%	60%		54%	47%	56%	89%	72%	26%
71.7%	73%	73%	73%	73%	80%	73%	68%	73%	73%	72%	68%	74%	68%	80%	68%	72%	80%	55%	64%	80%	66%
54.5%	52%	61%	59%	46%	54%	63%	56%	52%	61%	52%	69%	41%	61%	60%	60%	53%	62%	55%	69%	37%	21%
66.0%	75%	75%	69%	53%	53%	73%	75%	64%	69%	53%	69%	69%	69%	70%	67%	65%	67%	63%	83%	53%	53%
74.9%	84%	86%	84%	63%	74%	82%	64%	58%	66%	84%	92%	49%	74%	80%	92%	80%	83%	75%	92%	78%	33%
61.2%	66%	61%	70%	62%	39%	56%	62%	67%	55%	68%	62%	62%	61%	60%	62%	63%	56%	55%	53%	63%	83%
58.8%	68%	72%	68%		52%	41%	56%	45%	51%	56%	58%	39%	56%	45%	67%	77%	59%	69%	56%	62%	79%
74.4%	82%	74%	74%	82%	92%	52%	66%	84%	72%	92%	64%	72%	76%	68%	92%	79%	75%	45%	59%	70%	92%
55.7%	69%	57%	59%	57%	76%	41%	59%	60%	59%	57%	57%	34%	59%	46%	77%	67%	43%	43%	41%	64%	45%
84.2%	91%	65%	87%	91%	88%	72%	82%	90%	82%	88%	80%	88%	88%	85%	88%	91%	91%	85%	82%	79%	76%
57.9%	55%	64%	70%	42%	36%	73%	76%	56%	66%	64%	70%	59%	64%	67%	42%	52%	62%	39%	58%	49%	51%
55.4%	63%	52%	52%	63%	58%	47%	59%	58%	61%	62%	52%	63%	56%	57%	71%	64%	47%	54%	42%	55%	28%
60.5%	55%	55%	55%	63%	58%	66%	66%	57%	66%	53%	58%	53%	58%	69%	65%	58%	66%	64%	66%	60%	60%
54.7%	56%	63%	56%	45%	62%	63%	43%	49%	54%	58%	56%	43%	61%	59%	61%	58%	66%	66%	64%	41%	24%
73.8%	74%	86%	74%	61%	78%	87%	78%	74%	67%	57%	90%	80%	80%	80%	62%	75%	89%	66%	85%	51%	56%
50.0%	54%	49%	56%	49%	51%	46%	49%	51%	47%	52%	51%	47%	55%	57%	49%	52%	49%	50%	52%	47%	38%
69.3%	81%	76%	79%	81%	75%	44%	56%	71%	70%	76%	47%	71%	70%	50%	85%	73%	75%	63%	60%	74%	78%
60.7%	66%	69%	69%	64%	58%	63%	65%	68%	49%	69%	70%	62%	62%	56%	53%	55%	45%	54%	50%	69%	58%
79.7%	92%	83%	92%	83%	92%	75%	80%	75%	76%	65%	85%	60%	65%	85%	83%	92%	66%	73%	89%		83%
68.1%	79%	59%	79%	77%	61%	55%	77%	70%	68%	75%	59%	80%	75%	60%	64%	67%	70%	58%	68%	78%	52%
71.0%	80%	73%	81%	79%	75%	73%	70%	66%	75%	75%	66%	76%	75%	72%	71%	71%	58%	54%	64%	66%
58.8%	57%	59%	0%	57%	78%	64%	64%	64%	65%	57%	61%	71%	57%	61%	57%	57%	61%	61%	67%	39%	78%
73.9%	81%	78%	0%	81%	59%	73%	73%	73%	72%	81%	76%	66%	81%	76%	81%	81%	73%	76%	70%	100%	100%
62.7%	68%	68%	71%	79%	63%	60%	69%	64%	67%	73%	68%	45%	56%	64%	73%	73%	50%	46%	63%	34%	63%
61.5%	73%	53%	69%	53%	44%	64%	69%	69%	69%	63%	54%	56%	77%	64%	60%	82%	52%	51%	37%	65%	68%
58.1%	62%	66%	66%	60%	35%	65%	55%	59%	61%	57%	61%	60%	61%	61%	54%	61%	46%	61%	59%	63%	48%
72.3%	88%	84%	74%	63%	83%	88%	68%	53%	69%	72%	75%	57%	75%	75%	63%	75%	75%	77%	75%	75%	54%
76.1%	100%	80%		78%	85%	88%	86%	91%	91%	89%	71%	56%	85%	70%	83%	83%	48%	59%	83%	56%	39%
65.0%	74%	65%	73%	69%	66%	72%	67%	66%	65%	74%	67%	67%	66%	68%	71%	66%	58%	49%	60%	44%	58%
88.5%	100%	98%	0%	100%	78%	92%	92%	92%	91%	100%	95%	85%	100%	95%	100%	100%	95%	95%	89%	81%	81%
78.1%	79%	69%	81%	84%	70%	69%	79%	82%	76%	90%	77%	80%	69%	79%	85%	79%	81%	71%	81%	91%	69%
81.1%	81%	85%	81%	81%	88%	56%	79%	83%	73%	89%	92%	61%	81%	84%	85%	88%	80%	90%	81%	83%	83%
72.0%	77%	78%		79%	67%	62%	67%	62%	67%	70%	76%	74%	70%	79%	76%	73%	66%	76%	63%	79%	79%

Model Similarity Dendrogram

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