	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 75.5%	11th 71.7%	1st 75.7%	4th 74.6%	13th 70.0%	21st 65.2%	9th 72.3%	6th 74.3%	8th 73.8%	7th 74.0%	14th 70.0%	20th 65.7%	10th 72.1%	19th 68.0%	3rd 75.0%	5th 74.4%	15th 70.0%	18th 69.0%	16th 69.5%	12th 70.5%	17th 69.2%
71.4%	77%	77%	66%	68%	64%	90%	79%	77%	80%	68%	72%	53%	64%	64%	72%	76%	62%	64%	87%	69%	71%
70.6%	73%	76%	75%	71%	48%	79%	80%	76%	71%	77%	74%	74%	79%	65%	59%	59%	58%	82%	82%	75%	50%
63.0%	70%	76%	55%	65%	37%	37%	37%	64%	55%	70%	72%	80%	72%	72%	70%	70%	70%	72%	37%	72%	70%
76.6%	80%	76%	76%	76%	79%	65%	83%	80%	76%	83%	80%	79%	80%	58%	78%	84%	73%	71%	76%	79%	77%
82.4%	84%	81%	81%	85%	77%	77%	89%	96%	77%	85%	77%	77%	77%	77%	96%	92%	87%	77%	77%	77%	84%
63.2%	72%	64%	69%	75%	75%	56%	62%	64%	64%	64%	62%	59%	55%	59%	65%	64%	55%	67%	57%	57%	62%
77.4%	84%	79%	79%	85%	90%	65%	77%	83%	85%	77%	62%	66%	79%	82%	76%	78%	79%	69%	71%	83%	76%
62.1%	70%	62%	67%	71%	56%	39%	58%	68%	59%	65%	54%	59%	61%	49%	65%	75%	72%	62%	60%	68%	65%
73.4%	62%	62%	71%	67%	79%	73%	79%	84%	80%	73%	78%	49%	77%	75%	72%	68%	80%	90%	79%	73%	71%
78.1%	79%	79%	95%	85%	79%	79%	72%	77%	77%	79%	79%	76%	79%	79%	84%	84%	69%	48%	79%	79%	84%
82.8%	95%	100%	87%	78%	59%	86%	94%	100%	86%	79%	95%	86%	79%	73%	94%	90%	58%	59%	87%	96%	58%
71.5%	91%	79%	79%	80%	79%	59%	73%	77%	80%	68%	78%	79%	63%	61%	74%	74%	50%	49%	84%	54%
75.8%	73%	77%	73%	78%	77%	76%	72%	83%	70%	71%	77%	77%	77%	77%	77%	77%	69%	76%	77%	80%	77%
74.6%	76%	75%	76%	79%	73%	72%	74%	87%	79%	79%	69%	62%	75%	72%	79%	70%	83%	68%	73%	72%	74%
78.0%	77%	82%	84%	77%	78%	87%	78%	79%	80%	76%	76%	70%	87%	85%	77%	80%	70%	68%	87%	70%	70%
75.9%	78%	77%	85%	78%	85%	61%	75%	76%	75%	77%	75%	56%	76%	80%	78%	72%	81%	84%	70%	79%	75%
73.5%	72%	77%	92%	88%	56%	74%	63%	59%	76%	88%	71%	54%	65%	66%	82%	83%	81%	60%	81%	74%	82%
71.0%	75%	72%	79%	71%	65%	59%	64%	70%	67%	70%	67%	50%	68%	75%	77%	73%	77%	94%	62%	88%	67%
53.4%	57%	36%	51%	42%	75%	36%	62%	50%	57%	63%	51%	28%	57%	26%	70%	75%	58%	71%	41%	65%	50%
83.4%	95%	68%	94%	97%	87%	91%	86%	89%	95%	92%	63%	67%	89%	94%	72%	74%	88%	82%	85%	86%	57%
80.4%	87%	75%	83%	87%	80%	79%	77%	85%	82%	78%	76%	88%	87%	80%	85%	82%	61%	76%	84%	77%	80%
84.8%	93%	90%	95%	83%	84%	75%	88%	84%	83%	90%	81%	80%	83%	83%	92%	94%	79%	81%	82%	84%	77%
65.3%	56%	67%	68%	60%	58%	80%	67%	69%	65%	68%	71%	57%	57%	87%	71%	67%	67%	63%	61%	57%	55%
75.5%	78%	64%	78%	88%	83%	75%	78%	73%	77%	87%	77%	77%	78%	77%	72%	72%	69%	75%	78%	77%	52%
71.4%	74%	68%	70%	73%	76%	70%	63%	77%	73%	71%	71%	73%	73%	65%	74%	72%	65%	72%	73%	70%	76%
67.1%	74%	68%	66%	66%	55%	70%	66%	67%	67%	66%	72%	76%	66%	58%	69%	75%	54%	58%	76%	65%	76%
64.2%	69%	58%	72%	70%	70%	53%	64%	69%	72%	69%	55%	55%	68%	62%	66%	61%	68%	70%	62%	56%	59%
55.5%	60%	58%	56%	56%	55%	38%	53%	64%	62%	55%	49%	47%	55%	36%	70%	64%	69%	64%	46%	48%	60%
76.5%	85%	84%	92%	100%	83%	66%	84%	81%	84%	70%	57%	57%	62%	63%	84%	76%	71%	65%	73%	85%	85%
63.3%	75%	62%	76%	69%	82%	36%	62%	65%	66%	61%	61%	62%	71%	47%	64%	64%	66%	61%	52%	58%	69%
70.1%	70%	70%	70%	75%	72%	64%	72%	73%	73%	73%	65%	70%	71%	70%	71%	70%	63%	68%	70%	73%	70%
47.6%	43%	47%	50%	50%	37%	37%	46%	61%	62%	43%	37%	54%	62%	37%	43%	43%	43%	37%	62%	62%	43%
53.5%	51%	51%	55%	59%	55%	55%	79%	40%	47%	51%	55%	23%	55%	79%	51%	51%	51%	55%	55%	55%	51%
74.1%	82%	67%	74%	81%	82%	68%	73%	78%	79%	79%	67%	67%	67%	62%	80%	76%	82%	77%	61%	78%	77%
70.5%	80%	69%	81%	74%	56%	66%	71%	64%	73%	61%	65%	65%	71%	73%	79%	77%	76%	72%	78%	55%	75%
77.5%	81%	81%	83%	83%	65%	61%	77%	79%	78%	90%	90%	64%	100%	61%	80%	81%	73%	65%	65%	90%	81%
77.7%	78%	74%	75%	76%	70%	74%	76%	92%	85%	76%	70%	90%	76%	73%	79%	86%	77%	70%	86%	71%
82.4%	87%	88%	89%	82%	84%	77%	94%	86%	84%	87%	86%	77%	74%	77%	92%	89%	77%	81%	77%	52%	91%
62.2%	69%	65%	71%	60%	70%	59%	59%	61%	59%	75%	73%	52%	68%	67%	59%	65%	54%	45%	51%	63%	62%
82.4%	96%	95%	92%	78%	62%	62%	95%	91%	90%	95%	72%	92%	72%	72%	95%	95%	95%	62%	62%	62%	95%
59.1%	72%	52%	57%	66%	73%	46%	50%	57%	72%	60%	64%	45%	68%	48%	72%	66%	73%	69%	37%	45%	50%
78.1%	77%	76%	82%		85%	61%	82%	83%	79%	87%	83%	81%	79%	81%	75%	76%	73%	78%	75%		70%
76.0%	71%	77%	84%	82%	56%	71%	78%	57%	73%	85%	82%	72%	79%	77%	85%	78%	82%	92%	71%	82%	62%

Model Similarity Dendrogram

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