	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 71.0%	4th 70.9%	3rd 71.0%	6th 69.4%	18th 65.1%	15th 66.2%	11th 67.0%	14th 66.5%	12th 67.0%	8th 68.0%	1st 71.3%	19th 64.5%	5th 70.0%	13th 66.8%	10th 67.9%	7th 69.2%	16th 65.9%	17th 65.4%	9th 67.9%	20th 61.5%	21st 58.2%
73.3%	73%	78%	78%	81%	63%	64%	73%	67%	73%	78%	66%	70%	78%	76%	75%	81%	79%	80%	70%	73%	64%
66.4%	61%	70%	65%	65%	47%	67%	70%	63%	73%	59%	75%	68%	75%	68%	61%	58%	70%	66%	74%	74%	66%
72.2%	72%	78%	75%	75%	59%	72%	62%	75%	69%	75%	75%	75%	75%	69%	69%	75%	69%	76%	69%	62%	91%
88.3%	100%	78%	100%	78%	80%	89%	100%	89%	100%	78%	100%	80%	100%	78%	100%	95%	93%	81%	78%	80%	78%
81.9%	81%	88%	75%	81%	83%	68%	75%	81%	75%	90%	90%	81%	90%	81%	75%	95%	94%	97%	75%	80%	64%
62.1%	62%	66%	62%	62%	68%	68%	57%	79%	64%	63%	68%	68%	63%	58%	58%	62%	58%	55%	63%	49%	52%
64.5%	68%	61%	68%	68%	77%	65%	63%	69%	69%	66%	61%	61%	56%	49%	73%	68%	71%	67%	61%	47%	66%
70.1%	73%	67%	74%	73%	66%	62%	66%	73%	77%	66%	66%	71%	66%	77%	70%	77%	68%	73%	64%	71%	73%
82.0%	82%	84%	78%	81%	87%	60%	74%	87%	74%	95%	95%	75%	78%	78%	89%	89%	82%	86%	81%	90%	76%
71.9%	78%	80%	69%	71%	80%	80%	69%	72%	64%	71%	80%	80%	71%	64%	67%	69%	59%	62%	80%		73%
69.7%	82%	84%	82%	74%	61%	86%	74%	68%	68%	61%	74%	61%	68%	82%	60%	68%	60%	65%	76%	57%	52%
64.5%	65%	65%	73%	65%	55%	65%	62%	71%	66%	68%	65%	55%	65%	55%	68%	65%	62%	65%	59%	73%	68%
57.9%	49%	66%	58%	63%	68%	77%	49%	44%	57%	63%	71%	46%	69%	71%	59%	57%	68%	51%	77%	24%	29%
55.3%	56%	58%	53%	56%	60%	54%	61%	55%	58%	53%	61%	64%	58%	60%	50%	54%	56%	48%	58%	40%	48%
71.9%	74%	73%	74%	66%	75%	81%	63%	61%	66%	81%	75%	61%	66%	74%	75%	69%	77%	81%	89%	57%	71%
64.5%	75%	68%	81%	63%	63%	49%	61%	68%	64%	64%	61%	60%	74%	64%	63%	73%	63%	64%	61%	69%	46%
56.7%	68%	74%	80%	62%	54%	43%	54%	50%	54%	47%	54%	43%	57%	54%	75%	75%	43%	50%	58%	48%	48%
65.8%	84%	74%	74%	80%	80%	44%	60%	58%	49%	74%	62%	62%	74%	63%	69%	63%	61%	85%	51%	67%	48%
48.3%	65%	42%	61%	47%	40%	36%	51%	51%	47%	42%	56%	25%	50%	31%	77%	71%	61%	40%	30%	65%	26%
72.8%	77%	69%	62%	70%	70%	65%	77%	69%	77%	72%	77%	70%	78%	62%	73%	77%	73%	83%	78%	78%	72%
64.2%	66%	62%	69%	65%	66%	61%	70%	64%	70%	62%	70%	62%	65%	69%	66%	66%	64%	64%	69%	48%	51%
74.9%	70%	80%	84%	78%	74%	77%	78%	70%	73%	78%	84%	73%	78%	77%	71%	73%	79%	63%	78%	82%	52%
64.8%	60%	68%	71%	63%	78%	71%	68%	69%	71%	55%	71%	54%	63%	71%	63%	63%	64%	49%	63%	63%	63%
60.4%	58%	68%	58%	58%	55%	68%	55%	56%	56%	65%	73%	56%	65%	58%	64%	69%	56%	49%	80%	63%	39%
66.5%	63%	80%	73%	58%	72%	75%	74%	65%	61%	66%	73%	80%	73%	81%	63%	66%	44%	54%	73%	51%	51%
56.0%	49%	65%	55%	57%	57%	71%	53%	48%	48%	55%	67%	60%	55%	70%	50%	52%	60%	65%	60%	38%	40%
61.6%	55%	64%	64%	59%	59%	76%	56%	53%	56%	64%	78%	69%	64%	77%	58%	59%	59%	56%	69%	50%	48%
57.3%	64%	61%	64%	64%	55%	39%	64%	70%	64%	64%	60%	50%	64%	46%	71%	60%	46%	50%	40%	50%	57%
62.8%	80%	70%	71%	80%	63%	60%	71%	56%	56%	56%	58%	49%	56%	69%	65%	62%	52%	54%	61%	49%	80%
60.6%	75%	71%	68%	69%	59%	49%	53%	70%	70%	63%	64%	61%	57%	41%	66%	60%	76%	57%	62%	38%	43%
61.1%	60%	65%	60%	60%	65%	65%	58%	58%	63%	55%	68%	63%	65%	62%	51%	61%	65%	62%	68%	65%	44%
56.9%	60%	51%	54%	54%	69%	57%	66%	54%	60%	54%	54%	54%	54%	60%	60%	54%	60%	53%	60%	66%	40%
81.5%	82%	89%	86%	86%	69%	82%	73%	86%	79%	86%	86%	86%	86%	79%	79%	86%	79%	87%	79%	73%	73%
63.5%	69%	68%	66%	61%	56%	63%	68%	68%	68%	61%	68%	51%	64%	60%	69%	68%	63%	74%	60%	64%	44%
65.3%	71%	73%	73%	78%	30%	69%	73%	65%	74%	74%	73%	66%	78%	71%	50%	53%	54%	70%	61%	52%	63%
58.3%	61%	61%	61%	61%	39%	61%	61%	61%	56%	62%	64%	62%	69%	58%	44%	62%	56%	52%	62%	56%	55%
72.6%	86%	72%	69%	69%	71%	82%	69%	51%	72%	77%	69%	72%	74%	82%	77%	74%	72%	64%	82%	72%	69%
77.0%	79%	77%	87%	81%	87%	87%	87%	91%	82%	81%	75%	69%	91%	69%	81%	80%	62%	54%	75%	68%	54%
61.0%	71%	65%	59%	70%	63%	63%	64%	58%	62%	68%	59%	62%	62%	63%	69%	58%	58%	44%	52%	49%	61%
82.4%	92%	89%	86%	86%	69%	82%	73%	86%	79%	86%	86%	86%	86%	79%	79%	86%	79%	87%	79%	73%
77.6%	81%	81%	81%	89%	55%	65%	82%	84%	77%	87%	82%	69%	87%	58%	87%	77%	77%	80%	79%	74%	77%
75.1%	85%	72%	73%	78%	79%	65%	79%	74%	80%	80%	71%	71%	71%	85%	71%	73%	77%	71%	78%	71%	73%
68.7%	72%	73%	79%	79%	75%	62%	65%	52%	58%	60%	79%	72%	72%	72%	58%	72%	64%	77%	79%	65%	58%

Model Similarity Dendrogram

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