	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	5th 73.3%	11th 71.4%	3rd 73.9%	1st 76.0%	13th 71.1%	21st 64.6%	8th 73.0%	17th 69.3%	4th 73.8%	6th 73.1%	14th 70.9%	18th 68.8%	12th 71.2%	20th 68.0%	2nd 74.4%	7th 73.0%	15th 70.3%	19th 68.3%	16th 69.6%	10th 72.1%	9th 72.6%
68.2%	70%	68%	69%	69%	77%	73%	77%	68%	77%	73%	77%	48%	77%	54%	69%	72%	63%	47%	65%	70%	69%
65.0%	68%	76%	67%	67%	37%	71%	76%	65%	68%	54%	73%	67%	64%	81%	63%	56%	59%	74%	73%	53%	53%
64.7%	63%	63%	61%	67%	67%	67%	63%	61%	67%	63%	67%	62%	67%	67%	63%	63%	63%	67%	67%	67%	63%
71.3%	82%	83%	63%	83%	47%	63%	63%	74%	78%	74%	64%	64%	82%	65%		78%	74%	61%	83%	64%	81%
75.1%	76%	72%	76%	80%	72%	72%	76%	83%	72%	83%	72%	72%	72%	72%	80%	88%	72%	72%	72%	72%	72%
91.7%	100%	89%	83%	83%	77%	75%	100%	86%	89%	92%	100%	92%	100%	94%	92%	89%	100%	92%	92%	100%	100%
69.4%	74%	65%	74%	74%	75%	57%	59%	70%	70%	70%	56%	76%	56%	60%	82%	77%	75%	70%	46%	84%	87%
72.5%	80%	65%	86%	86%	76%	50%	59%	83%	70%	80%	65%	75%	65%	65%	92%	85%	70%	65%	65%	65%	75%
78.4%	60%	72%	82%	78%	89%	77%	100%	92%	92%	78%	73%	89%	70%	72%	67%	67%	76%	72%	92%	88%	60%
65.0%	64%	64%	66%	66%	64%	64%	58%	62%	67%	73%	79%	67%	59%	79%	72%	64%	58%	37%	64%		73%
65.8%	77%	75%	80%	75%	61%	64%	82%	73%	67%	58%	80%	70%	56%	52%	66%	68%	45%	50%	54%	71%	58%
69.6%	77%	77%	74%	77%	64%	72%	74%	68%	76%	63%	77%	79%	63%	79%	73%	69%	49%	47%	79%	52%	73%
83.5%	93%	85%	93%	86%	83%	89%	93%	88%	82%	90%	64%	87%	88%	64%	95%	83%	67%	67%	90%	90%	76%
83.8%	86%	86%	93%	79%	93%	76%	86%	74%	93%	79%	93%	93%	90%	66%	87%	80%	79%	81%	93%	80%	73%
82.1%	87%	86%	72%	88%	86%	82%	88%	86%	88%	88%	86%	72%	86%	86%	72%	72%	84%	85%	86%	72%	72%
78.5%	80%	71%	88%	94%	79%	71%	72%	80%	94%	94%	67%	72%	86%	75%	77%	86%	78%	45%	83%	73%	83%
76.8%		83%	94%	83%	94%	64%	70%	43%	80%	77%	83%	65%	69%	68%	83%	88%	80%	81%	77%	80%	74%
55.3%	49%	47%	59%	59%	67%	44%	42%	59%	55%	51%	44%	55%	55%	49%	59%	59%	56%	74%	54%	62%	63%
46.3%	41%	34%	40%	34%	73%	23%	48%	35%	54%	47%	41%	35%	57%	25%	65%	65%	57%	42%	34%	66%	57%
73.2%	82%	46%	76%	82%	80%	78%	79%	72%	62%	78%	46%	73%	78%	80%	70%	61%	75%	88%	65%	83%	83%
78.7%	89%	70%	88%	89%	85%	73%	77%	80%	76%	84%	76%	70%	83%	83%	79%	75%	72%	72%	62%	76%	93%
71.8%	80%	82%	77%	77%	62%	79%	71%	68%	71%	74%	74%	59%	66%	80%	71%	75%	65%	65%	71%	71%	70%
55.4%	62%	68%	51%	62%	52%	32%	62%	57%	49%	61%	53%	56%	57%	39%	57%	65%	52%	54%	55%	56%	64%
62.1%	59%	42%	66%	64%	64%	62%	64%	64%	59%	64%	64%	64%	64%	64%	55%	58%	64%	65%	64%		71%
84.8%	78%	90%	86%	90%	93%	78%	93%	74%	90%	100%	90%	93%	86%	93%	78%	75%	78%	83%	93%	93%	47%
73.2%	77%	91%	76%	89%	62%	63%	89%	66%	77%	77%	83%	66%	62%	69%	70%	80%	61%	66%	79%	70%	64%
70.9%	70%	68%	74%	72%	74%	61%	71%	70%	67%	73%	63%	72%	72%	83%	69%	74%	74%	74%	63%	73%	72%
59.4%	62%	65%	72%	66%	72%	40%	62%	69%	75%	67%	48%	31%	65%	39%	79%	72%	60%	63%	50%	40%	51%
73.0%	78%	94%	95%	95%	68%	72%	77%	77%	77%	64%	56%	56%	64%	71%	78%	67%	76%	60%	78%	56%	75%
61.7%	67%	59%	72%	72%	77%	34%	61%	58%	55%	50%	55%	58%	59%	49%	69%	61%	62%	82%	62%	63%	71%
79.8%	82%	81%	80%	80%	77%	80%	80%	74%	80%	80%	82%	94%	82%	82%	77%	77%	74%	76%	72%	89%	77%
44.9%	43%	31%	31%	56%	61%	31%	61%	56%	61%	43%	48%	61%	31%	31%	43%	43%	45%	61%	31%	31%	43%
64.7%	63%	63%	61%	67%	67%	67%	63%	61%	67%	63%	67%	62%	67%	67%	63%	63%	63%	67%	67%	67%	63%
82.0%	92%	76%	81%	93%	100%	64%	73%	72%	72%	90%	80%	80%	80%	80%	91%	88%	94%	90%	54%	87%	85%
64.3%	67%	65%	62%	66%	31%	75%	60%	60%	61%	61%	52%	67%	61%	73%	72%	72%	77%	59%	73%	67%	70%
69.1%	74%	73%	75%	57%	50%	66%	74%	74%	65%	59%	71%	69%	74%	66%	70%	64%	70%	69%	82%	70%	80%
88.6%	94%	82%	88%	94%	94%	92%	94%	60%	94%	89%	100%	82%	94%	82%	87%	83%	82%	82%	94%	94%	100%
86.9%	89%	100%	93%	92%	92%	71%	93%	75%	92%	100%	77%	72%	94%	72%	100%	93%	88%	67%	72%	93%	100%
61.3%	62%	63%	65%	65%	48%	60%	62%	59%	65%	65%	66%	56%	60%	67%	55%	56%	61%	57%	67%	66%	62%
79.2%		67%	67%	94%	67%	67%	82%	92%	100%	94%	89%	61%	67%	67%	94%	94%	94%	61%	67%	67%	94%
69.4%	76%	70%	59%	66%	72%	53%	70%	61%	76%	81%	78%	60%	78%	44%	78%	82%	72%	74%	55%	85%	68%
61.0%	57%	63%	63%	63%	62%	36%	59%	57%	56%	53%	74%	56%	63%	74%	68%	63%	67%	71%	56%	58%	63%
90.5%		100%	100%	88%	67%	91%	77%	74%	88%	88%	94%	100%	94%	94%	94%	91%	90%	100%	91%	94%	94%

Model Similarity Dendrogram

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