	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	2nd 73.7%	10th 70.9%	5th 72.6%	1st 74.2%	17th 69.6%	20th 65.0%	11th 70.5%	6th 72.3%	8th 71.8%	3rd 73.4%	14th 70.1%	21st 64.8%	4th 73.3%	12th 70.4%	7th 71.9%	9th 71.3%	19th 68.1%	15th 70.0%	16th 69.9%	13th 70.1%	18th 69.5%
67.1%	66%	76%	66%	70%	59%	83%	62%	70%	71%	66%	66%	76%	70%	70%	59%	59%	68%	57%	71%	62%	62%
63.0%	57%	71%	71%	76%	40%	66%	68%	66%	76%	56%	52%	65%	56%	65%	55%	52%	76%	71%	71%	58%	56%
92.0%	90%	90%	85%	85%	100%	100%	85%	78%	78%	90%	100%	91%	100%	100%	90%	90%	90%	100%	100%	100%	90%
79.7%	89%	70%	70%	89%	76%	70%	76%	89%	87%	79%	76%	76%	89%	65%	91%	87%	89%	77%	76%	76%	76%
83.0%	86%	86%	79%	80%	86%	86%	80%	86%	80%	86%	86%	86%	86%	86%	80%	82%	72%	79%	86%	86%	80%
69.1%	79%	79%	77%	77%	79%	56%	62%	79%	79%	70%	70%	56%	62%	62%	69%	70%	62%	70%	62%	62%	69%
76.0%	87%	87%	79%	87%	84%	66%	72%	75%	74%	80%	69%	58%	76%	69%	76%	87%	69%	89%	69%	72%	70%
50.5%	54%	41%	56%	56%	44%	36%	49%	56%	45%	52%	49%	45%	45%	42%	66%	55%	54%	52%	49%	44%	71%
66.3%	68%	59%	59%	69%	69%	48%	65%	77%	65%	68%	67%	83%	69%	59%	71%	67%	69%	63%	73%	69%	56%
70.5%	76%	76%	77%	77%	76%	76%	66%	32%	76%	79%	63%	76%	79%	76%	72%	62%	55%	55%	76%	76%	79%
64.4%	67%	72%	89%	72%	44%	60%	67%	72%	60%	75%	67%	85%	66%	60%	61%	77%	46%	54%	66%	67%	26%
69.2%	67%	73%	73%	73%	80%	60%	68%	89%	80%	68%	68%	77%	60%	72%	65%	68%	39%	61%	73%	72%	67%
65.8%	67%	76%	60%	63%	44%	57%	67%	79%	69%	66%	76%	76%	67%	76%	76%	67%	40%	69%	76%		46%
80.8%	83%	81%	81%	84%	75%	81%	87%	81%	87%	78%	81%	69%	78%	81%	68%	88%	88%	84%	81%	81%	80%
84.5%	90%	90%	90%	100%	90%	84%	90%	84%	84%	90%	90%	66%	90%	78%	90%	84%	75%	67%	90%	75%	77%
69.4%	79%	70%	79%	70%	69%	66%	66%	70%	61%	79%	63%	45%	79%	79%	79%	68%	64%	64%	68%	66%	73%
62.6%	61%	72%	72%	72%	76%	48%	56%	43%	56%	72%	58%	63%	56%	58%	72%	63%	68%	41%	63%	68%	76%
76.4%	71%	68%	83%	83%	83%	62%	70%	83%	76%	83%	68%	62%	74%	83%	83%	79%	77%	82%	69%	83%	83%
70.0%	83%	59%	63%	57%	69%	47%	70%	91%	75%	84%	72%	50%	91%	50%	91%	76%	78%	58%	41%	85%	80%
72.3%	83%	51%	81%	77%	81%	82%	75%	75%	77%	83%	66%	53%	81%	73%	50%	75%	69%	75%	66%	72%
65.9%	70%	77%	74%	74%	70%	64%	69%	73%	77%	70%	77%	49%	73%	67%	52%	55%	55%	59%	64%	65%	50%
51.3%	51%	46%	51%	51%	55%	47%	58%	58%	52%	46%	47%	40%	54%	55%	49%	58%	52%	63%	52%	42%	50%
63.5%	63%	66%	66%	53%	54%	69%	66%	66%	53%	71%	60%	60%	66%	77%	66%	65%	66%	62%	66%	58%	60%
70.4%	64%	63%	64%	64%	76%	64%	64%	64%	70%	71%	76%	76%	76%	76%	77%	69%	69%	67%	76%	76%	76%
80.0%	85%	82%	83%	74%	81%	90%	83%	78%	85%	81%	83%	69%	81%	69%	80%	83%	77%	75%	81%	81%	79%
52.1%	56%	62%	51%	55%	42%	56%	55%	59%	51%	48%	52%	51%	51%	51%	55%	55%	47%	46%	59%	40%	52%
70.3%	79%	59%	76%	76%	76%	57%	66%	76%	70%	66%	49%	54%	71%	77%	79%	62%	83%	85%	54%	62%	100%
70.4%	70%	70%	77%	77%	69%	51%	79%	69%	69%	100%	69%	55%	79%	63%	79%	69%	69%	70%	62%	70%	62%
76.2%	83%	92%	83%	83%	83%	68%	77%	92%	88%	60%	60%	60%	65%	76%	83%	78%	69%	69%	88%	67%
72.1%	75%	73%	79%	76%	79%	49%	79%	70%	79%	70%	79%	63%	70%	70%	79%	79%	70%	70%	57%	79%	70%
69.4%	66%	66%	73%	66%	75%	69%	73%	80%	80%	73%	69%	61%	66%	69%	68%	69%	68%	66%	66%	66%	68%
52.9%	51%	51%	49%	49%	57%	57%	49%	62%	57%	51%	49%	57%	57%	39%	51%	51%	51%	57%	57%	57%	51%
72.5%	66%	66%	59%	81%	81%	81%	59%	66%	59%	66%	81%	89%	81%	81%	66%	66%	66%	81%	81%	81%	66%
64.2%	68%	53%	62%	75%	64%	60%	56%	64%	62%	64%	64%	64%	64%	64%	64%	71%	66%	71%	58%	68%	66%
68.4%	73%	58%	62%	73%	72%	45%	64%	77%	69%	82%	64%	43%	69%	73%	77%	83%	76%	68%	52%	77%	80%
65.4%	71%	66%	71%	71%	44%	63%	76%	66%	66%	72%	72%	52%	76%	58%	63%	56%	66%	58%	63%	76%	67%
77.8%	91%	91%	82%	91%	69%	81%	77%	63%	81%	82%	82%	69%	84%	84%	65%	65%	59%	74%	81%		85%
87.1%	89%	89%	89%	86%	86%	86%	100%	89%	89%	86%	86%	86%	86%	86%	89%	89%	85%	89%	86%	89%	69%
67.7%	71%	69%	67%	71%	64%	67%	71%	69%	67%	65%	67%	63%	71%	61%	75%	69%	66%	69%	67%	67%	66%
86.1%	91%	90%	91%	85%	57%	57%	85%	83%	78%	90%	92%	91%	100%	100%	90%	90%	92%	100%	100%	57%	90%
65.8%	66%	61%	69%	77%	65%	46%	63%	69%	74%	83%	70%	43%	77%	46%	62%	69%	67%	78%	61%	63%	73%
80.6%	88%	83%	83%	88%	84%	57%	81%	81%	78%	81%	83%	57%	81%	88%	83%	84%	92%	92%	72%	81%	75%
75.4%	77%	70%	70%	79%	67%	76%	79%	62%	79%	76%	76%	76%	79%	93%	76%	76%	70%	71%	76%	79%	76%

Model Similarity Dendrogram

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