	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 71.3%	11th 69.7%	2nd 71.5%	4th 70.5%	18th 65.1%	10th 69.9%	12th 69.6%	16th 66.5%	15th 67.6%	1st 71.7%	8th 70.3%	19th 64.9%	7th 70.3%	6th 70.4%	13th 69.3%	5th 70.5%	14th 68.2%	21st 63.7%	9th 70.3%	17th 66.3%	20th 64.3%
76.9%	66%	73%	81%	71%	68%	83%	89%	85%	81%	85%	81%	81%	81%	83%	70%	72%	68%	73%	79%	81%	63%
54.3%	56%	50%	49%	68%	39%	52%	57%	54%	45%	68%	48%	49%	48%	63%	66%	64%	52%	42%	55%	53%	63%
81.5%	79%	77%	86%	86%	69%	82%	73%	79%	69%	86%	86%	86%	93%	79%	86%	93%	86%	74%	71%	86%	86%
79.8%	75%	77%	89%	77%	73%	91%	77%	71%	75%	78%	89%	78%	78%	77%	73%	84%	91%	88%	77%	78%	80%
81.5%	84%	78%	89%	89%	84%	85%	84%	84%	80%	72%	72%	78%	76%	76%	78%	83%	94%	79%	84%	84%	79%
68.8%	58%	64%	58%	58%	66%	67%	76%	69%	72%	80%	67%	67%	80%	76%	63%	63%	73%	73%	80%	68%	67%
66.5%	67%	68%	71%	75%	65%	66%	67%	73%	63%	68%	63%	63%	63%	68%	73%	72%	73%	47%	68%	59%	64%
76.5%	85%	85%	80%	80%	85%	56%	81%	81%	74%	81%	74%	72%	80%	77%	85%	75%	58%	64%	72%	78%	83%
68.5%	65%	65%	62%	64%	58%	58%	62%	80%	70%	73%	72%	77%	65%	69%	64%	62%	72%	84%	65%	76%	76%
74.4%	86%	74%	75%	75%	75%	77%	75%	70%	75%	78%	75%	78%	78%	65%	77%	75%	73%	63%	64%	76%	78%
72.6%	83%	80%	77%	77%	71%	89%	71%	74%	71%	70%	76%	64%	70%	76%	71%	76%	84%	54%	75%	64%	52%
65.6%	73%	65%	65%	74%	69%	65%	65%	65%	63%	64%	65%	64%	65%	74%	67%	65%	74%	54%	64%	54%	64%
64.1%	63%	69%	63%	77%	64%	76%	57%	52%	63%	72%	68%	50%	68%	72%	74%	72%	61%	49%	68%	57%	51%
50.8%	61%	58%	60%	48%	35%	47%	60%	46%	53%	58%	53%	64%	53%	56%	38%	55%	41%	56%	62%	35%	28%
79.8%	91%	78%	83%	83%	82%	82%	75%	69%	73%	92%	79%	57%	79%	75%	89%	88%	79%	68%	76%	89%	89%
62.8%	60%	60%	62%	54%	60%	68%	71%	56%	71%	66%	65%	66%	65%	69%	63%	59%	65%	57%	68%	54%	60%
67.1%	79%	83%	87%	72%	63%	71%	63%	58%	71%	69%	79%	50%	58%	69%	64%	72%	65%	44%	69%	63%	61%
56.0%	60%	57%	57%	60%	78%	35%	46%	57%	53%	46%	46%	53%	57%	51%	68%	64%	58%	68%	44%	49%	68%
33.9%	36%	28%	32%	28%	60%	16%	41%	28%	36%	36%	36%	26%	28%	28%	47%	52%	41%	24%	14%	28%	46%
62.4%	69%	65%	60%	57%	49%	63%	71%	57%	58%	74%	63%	51%	62%	53%	65%	70%	54%	71%	72%	63%	63%
63.7%	68%	63%	71%	71%	60%	83%	61%	52%	68%	79%	68%	50%	68%	82%	50%	51%	43%	62%	89%	64%	35%
74.0%	77%	77%	77%	76%	61%	91%	70%	62%	68%	84%	75%	62%	75%	85%	80%	79%	78%	74%	91%	75%	38%
71.0%	63%	68%	68%	67%	89%	86%	68%	84%	84%	68%	77%	60%	72%	78%	68%	68%	72%	60%	63%	68%	60%
59.4%	68%	68%	60%	68%	50%	61%	54%	54%	49%	68%	61%	39%	60%	56%	68%	64%	54%	50%	65%	73%	58%
54.4%	57%	62%	53%	49%	54%	62%	53%	48%	56%	57%	62%	56%	56%	49%	54%	61%	49%	66%	63%	38%	37%
45.0%	45%	51%	51%	50%	51%	47%	48%	40%	41%	48%	53%	41%	50%	48%	37%	52%	47%	45%	49%	24%	28%
67.7%	72%	75%	75%	70%	59%	64%	70%	55%	68%	75%	64%	68%	76%	75%	55%	65%	73%	68%	73%	66%	55%
77.6%	75%	83%	84%	84%	40%	79%	80%	84%	76%	79%	90%	75%	84%	79%	66%	76%	79%	69%	89%	90%	68%
69.4%	78%	80%	78%	78%	68%	62%	80%	65%	64%	60%	68%	73%	64%	69%	74%	67%	60%	60%	73%	69%	68%
66.8%	73%	63%	78%	80%	81%	57%	69%	68%	56%	65%	68%	60%	60%	60%	80%	71%	72%	61%	56%	56%	69%
69.1%	68%	67%	65%	68%	66%	76%	61%	55%	59%	77%	72%	61%	72%	78%	69%	76%	68%	47%	84%	78%	84%
48.9%	52%	53%	44%	44%	59%	47%	56%	50%	59%	44%	44%	44%	38%	50%	38%	38%	44%	59%	58%	62%	44%
80.4%	79%	77%	86%	86%	69%	82%	73%	79%	69%	86%	86%	86%	93%	79%	79%	79%	86%	69%	71%	86%	88%
71.3%	79%	79%	79%	65%	49%	68%	78%	76%	78%	63%	78%	67%	67%	82%	72%	80%	68%	74%	84%	50%	62%
72.0%	76%	58%	76%	76%	47%	80%	77%	73%	79%	79%	71%	63%	76%	62%	76%	79%	74%	73%	63%	69%	84%
69.3%	64%	72%	75%	60%	41%	78%	72%	74%	73%	68%	75%	77%	77%	78%	70%	67%	68%	60%	79%	69%	59%
84.3%	86%	85%	86%	76%	91%	87%	79%	79%	84%	76%	86%	77%	89%	86%	86%	90%	87%	86%	88%	88%	78%
60.7%	71%	56%	69%	69%	69%	61%	77%	62%	69%	69%	57%	49%	57%	55%	62%	58%	42%	45%	55%	46%	77%
84.2%	85%	88%	85%	88%	85%	100%	86%	75%	75%	100%	79%	91%	91%	100%	91%	80%	75%	71%	92%	82%	49%
87.9%	91%	85%	95%	95%	78%	91%	81%	88%	78%	95%	95%	95%	98%	88%	95%	88%	95%	78%	80%	75%	81%
72.8%	72%	75%	80%	80%	58%	66%	74%	70%	75%	75%	77%	74%	80%	66%	81%	80%	80%	72%	67%	63%	64%
76.2%	74%	85%	67%	74%	71%	59%	74%	74%	67%	66%	85%	71%	89%	89%	71%	78%	80%	78%	89%	80%	80%
82.7%	97%	75%	86%	86%	91%	90%	90%	86%	97%	86%	75%	76%	86%	79%	75%	67%	75%	82%	75%	87%	76%

Model Similarity Dendrogram

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