	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	1st 73.5%	3rd 72.5%	2nd 73.1%	12th 69.0%	20th 64.8%	13th 68.0%	7th 70.5%	8th 70.4%	15th 67.3%	4th 71.4%	6th 71.0%	16th 66.5%	5th 71.2%	17th 65.3%	11th 69.2%	9th 69.8%	19th 64.9%	21st 64.4%	10th 69.4%	14th 67.3%	18th 65.0%
65.9%	72%	64%	69%	67%	58%	57%	64%	64%	63%	74%	64%	43%	78%	67%	72%	69%	73%	71%	63%	74%	58%
69.4%	79%	69%	77%	73%	33%	80%	62%	76%	69%	67%	78%	76%	78%	76%	62%	62%	76%	58%	76%	69%	62%
81.1%	92%	78%	84%	84%	68%	84%	78%	78%	68%	84%	92%	92%	78%	78%	71%	78%	71%	84%	78%	92%	92%
71.1%	80%	60%	64%	62%	61%	77%	75%	84%	75%	77%	80%	61%	77%	80%	63%	86%	77%	70%	63%	61%	61%
75.8%	86%	74%	86%	80%	65%	93%	86%	70%	70%	73%	74%	80%	65%	73%	86%	73%	65%	70%	86%	63%	74%
80.3%	74%	83%	74%	74%	100%	87%	73%	100%	81%	81%	88%	71%	78%	88%	71%	67%	84%	83%	78%	77%	74%
73.4%	81%	78%	77%	81%	78%	73%	84%	81%	60%	82%	78%	62%	73%	62%	70%	66%	76%	76%	79%	62%	62%
64.0%	70%	70%	64%	67%	72%	51%	71%	66%	63%	66%	61%	61%	68%	51%	77%	67%	60%	67%	54%	61%	58%
87.0%	87%	96%	91%	91%	92%	66%	85%	92%	86%	83%	92%	91%	93%	91%	76%	88%	85%	84%	85%		85%
61.0%	69%	79%	67%	71%	61%	61%	55%	62%	61%	69%	61%	61%	69%	61%	62%	55%	41%	33%	61%	61%	62%
72.8%	80%	80%	80%	77%	77%	79%	80%	80%	67%	62%	77%	77%	67%	62%	76%	67%	51%	47%	91%	67%	85%
68.8%	78%	74%	71%	66%	80%	71%	71%	70%	58%	68%	71%	72%	62%	71%	73%	70%	48%	63%	71%	70%	66%
70.3%	69%	71%	71%	71%	74%	85%	64%	61%	68%	64%	80%	64%	71%	71%	68%	67%	68%	68%	85%	68%	68%
78.9%	86%	89%	89%	78%	72%	77%	80%	81%	81%	83%	81%	52%	83%	52%	76%	81%	90%	84%	83%	78%	81%
72.5%	76%	75%	76%	75%	76%	76%	76%	68%	73%	73%	76%	73%	71%	67%	71%	71%	61%	62%	76%	73%	77%
73.2%	79%	74%	90%	79%	71%	59%	74%	79%	67%	85%	68%	55%	85%	57%	83%	72%	69%	74%	71%		72%
60.0%	69%	65%	69%	65%	57%	52%	65%	50%	57%	69%	61%	50%	39%	65%	57%	64%	57%	61%	57%	61%	69%
55.0%	73%	57%	65%	73%	67%	26%	42%	52%	52%	61%	48%	80%	67%	39%	49%	60%	67%	28%	57%	50%	43%
63.9%	61%	48%	70%	62%	47%	52%	77%	77%	59%	76%	70%	47%	66%	52%	76%	73%	71%	68%	48%	84%	58%
68.1%	77%	72%	77%	61%	58%	63%	77%	88%	58%	77%	58%	58%	77%	58%	76%	77%	58%	69%	76%	58%	58%
53.9%	52%	57%	58%	42%	44%	64%	63%	49%	60%	51%	59%	63%	63%	61%	42%	52%	33%	49%	55%	68%	47%
73.8%	74%	83%	83%	78%	55%	79%	77%	66%	72%	66%	90%	77%	73%	80%	63%	71%	69%	70%	75%	72%	77%
71.7%	67%	78%	67%	67%	86%	70%	73%	92%	78%	85%	61%	73%	86%	73%	60%	66%	57%	61%	64%	86%	55%
76.3%	78%	86%	82%	82%	78%	78%	73%	75%	78%	77%	78%	72%	73%	83%	77%	91%	73%	49%	73%	73%	73%
77.6%	71%	84%	68%	84%	80%	84%	84%	86%	84%	88%	71%	61%	84%	61%	82%	76%	84%	84%	89%	84%	41%
56.0%	52%	63%	60%	52%	54%	57%	62%	50%	56%	60%	62%	32%	54%	62%	44%	59%	62%	51%	58%	72%	55%
73.4%	78%	76%	79%	86%	79%	58%	76%	78%	72%	100%	63%	54%	76%	63%	80%	79%	71%	66%	80%	71%	57%
62.5%	64%	70%	68%	71%	71%	47%	63%	68%	72%	64%	63%	53%	68%	38%	71%	62%	58%	66%	53%	59%	64%
68.6%	74%	74%	80%	79%	93%	61%	78%	68%	63%	64%	69%	72%	55%	64%	69%	74%	55%	58%	55%	72%	64%
65.0%	67%	74%	74%	72%	63%	51%	55%	74%	74%	67%	69%	63%	69%	41%	74%	72%	70%	88%	53%	59%	35%
79.0%	91%	85%	78%	82%	66%	89%	85%	78%	83%	72%	91%	85%	91%	74%	79%	77%	50%	77%	71%	79%	75%
76.0%	74%	80%	74%	0%	90%	74%	80%	80%	90%	74%	67%	67%	80%	80%	87%	80%	82%	90%	80%	86%	80%
50.9%	64%	53%	58%	0%	44%	58%	52%	53%	44%	58%	64%	64%	52%	52%	47%	52%	51%	59%	52%	44%	47%
63.5%	73%	61%	65%	73%	59%	59%	63%	61%	68%	69%	62%	58%	61%	62%	68%	68%	65%	62%	58%	58%	61%
56.7%	70%	72%	72%	76%	24%	67%	44%	44%	32%	49%	49%	68%	68%	60%	58%	49%	47%	49%	76%	49%	68%
54.3%	50%	55%	62%	62%	34%	58%	55%	58%	44%	51%	58%	61%	62%	64%	51%	51%	44%	54%	61%	47%	58%
60.4%	68%	61%	58%	58%	54%	64%	54%	48%	61%	64%	63%	61%	60%	66%	61%	64%	61%	56%	61%	61%	64%
70.4%	84%	72%	77%	70%	52%	84%	84%	77%	84%	77%	65%	64%	77%	64%	74%	70%	56%	51%	70%	52%	74%
83.0%	83%	82%	88%	88%	57%	77%	90%	83%	90%	77%	86%	84%	83%	69%	90%	91%	85%	82%	84%	100%	75%
79.3%	84%	78%	84%	84%	68%	84%	78%	78%	68%	84%	92%	92%	78%	78%	78%	78%	76%	90%	78%	65%	71%
73.4%	78%	76%	78%	78%	61%	74%	79%	75%	73%	78%	78%	74%	91%	66%	72%	84%	71%	27%	79%	71%	78%
55.9%	66%	60%	51%	58%	51%	47%	62%	53%	55%	66%	56%	66%	55%	58%	54%	57%	56%	50%	53%	48%	51%
64.5%	61%	80%	69%	69%	57%	69%	61%	53%	55%	55%	80%	69%	57%	69%	78%	66%	65%	60%	69%	53%	60%

Model Similarity Dendrogram

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