	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	3rd 70.7%	10th 69.4%	8th 69.5%	9th 69.5%	12th 68.9%	19th 66.8%	13th 68.6%	18th 67.5%	15th 68.1%	4th 70.0%	7th 69.7%	21st 62.1%	11th 69.4%	14th 68.3%	2nd 71.1%	5th 69.9%	16th 68.0%	20th 63.5%	6th 69.7%	17th 67.9%	1st 71.6%
70.8%	68%	71%	83%	75%	63%	79%	64%	68%	67%	73%	68%	68%	70%	70%	75%	70%	72%	68%	71%	72%	72%
84.3%	87%	79%	86%	91%	70%	86%	82%	84%	68%	89%	85%	88%	85%	85%	85%	95%	87%	78%	89%	84%	87%
79.6%	75%	78%	83%	81%	75%	91%	77%	83%	75%	83%	87%	91%	83%	82%	83%	71%	78%	79%	75%	71%	71%
62.3%	67%	64%	65%	73%	78%	38%	70%	68%	68%	64%	68%	41%	68%	60%	63%	63%	55%	56%	62%	57%	61%
81.9%	78%	78%	76%	73%	83%	84%	69%	76%	84%	82%	89%	89%	91%	89%	78%	89%	89%	84%	89%	79%	71%
73.5%	67%	69%	60%	63%	64%	80%	70%	64%	75%	75%	75%	80%	75%	80%	75%	73%	74%	79%	80%	90%	75%
62.7%	62%	62%	62%	62%	66%	45%	62%	68%	65%	67%	62%	67%	66%	59%	65%	64%	69%	59%	62%	54%	69%
67.0%	75%	67%	63%	66%	72%	57%	75%	67%	71%	75%	62%	71%	67%	68%	68%	69%	67%	61%	58%	71%	57%
71.0%	74%	65%	66%	67%	68%	60%	66%	75%	73%	70%	70%	74%	73%	74%	71%	81%	79%	69%	70%	89%	56%
77.8%	82%	83%	72%	87%	76%	74%	88%	86%	87%	75%	87%	54%	87%	79%	75%	76%	87%	78%	77%	56%	68%
59.3%	62%	64%	64%	72%	50%	79%	60%	72%	57%	60%	64%	41%	64%	50%	73%	47%	39%	32%	67%	55%	73%
63.6%	81%	72%	63%	74%	77%	55%	63%	70%	67%	63%	74%	20%	74%	74%	54%	74%	63%	40%	67%	50%	60%
45.5%	42%	47%	45%	54%	46%	61%	40%	36%	36%	45%	54%	24%	45%	44%	44%	44%	47%	44%	61%	49%	48%
58.8%	60%	62%	66%	50%	56%	60%	67%	51%	56%	53%	59%	53%	60%	66%	61%	57%	51%	50%	68%		70%
84.9%	87%	89%	84%	87%	90%	84%	92%	73%	90%	88%	81%	78%	89%	91%	81%	87%	87%	77%	88%	77%	83%
85.4%	83%	88%	90%	81%	78%	77%	89%	85%	83%	90%	90%	90%	92%	89%	88%	85%	82%	71%	91%	79%	92%
72.0%	76%	78%	78%	78%	74%	82%	72%	64%	69%	69%	62%	70%	64%	65%	81%	76%	63%	67%	82%	65%	78%
63.0%	72%	70%	62%	68%	76%	49%	62%	66%	62%	60%	68%	63%	66%	50%	64%	67%	56%	58%	53%	65%	65%
38.4%	44%	32%	28%	28%	69%	6%	43%	30%	47%	41%	20%	28%	28%	20%	61%	56%	37%	44%	12%	61%	72%
67.1%	68%	68%	74%	67%	69%	74%	67%	77%	65%	63%	67%	69%	61%	67%	62%	66%	63%	57%	67%	70%	69%
52.2%	47%	52%	60%	60%	48%	66%	47%	46%	47%	60%	50%	39%	52%	52%	54%	55%	55%	25%	64%	52%	65%
64.4%	59%	58%	65%	65%	68%	82%	62%	61%	64%	69%	69%	43%	57%	68%	69%	61%	61%	49%	82%	70%	71%
53.4%	57%	51%	56%	41%	54%	48%	59%	58%	60%	55%	56%	60%	53%	56%		57%	53%	60%	43%	46%	46%
78.5%	78%	79%	81%	71%	79%	84%	80%	62%	81%	80%	88%	58%	88%	78%	85%	76%	90%	75%	73%	80%	82%
70.2%	70%	81%	73%	73%	59%	62%	75%	66%	63%	59%	73%	73%	66%	73%	71%	71%	58%	71%	82%		84%
64.2%	62%	67%	60%	63%	60%	76%	65%	48%	61%	67%	67%	69%	61%	70%	67%	59%	69%	54%	66%	67%	70%
83.7%	89%	81%	87%	87%	87%	74%	73%	78%	85%	90%	86%	80%	84%	85%	83%	90%	89%	82%	83%	76%	88%
81.4%	91%	90%	88%	82%	81%	71%	91%	87%	72%	88%	80%	77%	80%	87%	78%	84%	84%	70%	74%	72%	82%
72.5%	79%	76%	73%	79%	76%	65%	74%	73%	67%	63%	78%	26%	79%	73%	80%	79%	77%	81%	73%	75%	76%
67.4%	73%	69%	71%	71%	67%	70%	63%	69%	68%	72%	67%	75%	66%	63%	73%	69%	62%	53%	69%	60%	66%
66.9%	64%	65%	66%	70%	63%	71%	56%	65%	60%	75%	63%	46%	63%	69%	83%	70%	65%	71%	77%	59%	83%
79.1%	82%	81%	77%	78%	84%	69%	82%	77%	85%	77%	73%	69%	76%	78%	77%	78%	81%	80%	85%	88%	85%
51.5%	46%	50%	54%	53%	48%	61%	49%	54%	47%	54%	57%	61%	55%	53%	47%	54%	50%	51%	47%	44%	47%
82.5%	88%	86%	79%	73%	70%	72%	85%	82%	86%	73%	89%	77%	90%	78%	84%	87%	87%	90%	77%	91%	89%
61.8%	66%	56%	65%	60%	55%	54%	53%	68%	59%	74%	60%	58%	66%	57%	64%	62%	63%	65%	60%	68%	64%
43.2%	48%	47%	48%	45%	43%	47%	43%	38%	39%	47%	41%	41%	41%	41%	44%	42%	40%	44%	47%	36%	46%
67.8%	66%	64%	66%	58%	70%	69%	62%	58%	70%	70%	74%	60%	70%	79%	68%	60%	74%	62%	80%	65%	78%
65.7%	74%	67%	68%	72%	67%	66%	73%	68%	64%	69%	63%	55%	68%	55%	74%	68%	62%	70%	55%	51%	71%
70.7%	76%	74%	79%	81%	71%	70%	71%	73%	69%	74%	73%	66%	68%	68%	78%	70%	65%	48%	68%	70%	73%
87.2%	92%	89%	85%	86%	92%	76%	90%	85%	92%	85%	80%	76%	84%	85%	92%	85%	89%	88%	92%	96%	92%
71.3%	78%	76%	77%	74%	78%	57%	77%	76%	70%	84%	80%	69%	63%	69%	75%	74%	67%	56%	58%	70%	69%
89.8%	92%	90%	89%	90%	91%	90%	86%	90%	100%	90%	81%	80%	91%	82%	81%	94%	89%	89%	100%	99%	92%
53.8%	51%	51%	51%	58%	53%	51%	54%	58%	55%	49%	58%	55%	55%	58%	51%	52%	51%	44%	55%	55%	64%

Model Similarity Dendrogram

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