	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	3rd 74.1%	13th 71.4%	2nd 75.5%	1st 75.5%	14th 71.2%	19th 66.7%	4th 73.9%	11th 71.7%	9th 72.8%	5th 73.7%	12th 71.6%	21st 65.4%	8th 72.8%	20th 66.7%	6th 73.6%	7th 73.4%	16th 70.8%	17th 69.2%	18th 69.0%	10th 72.0%	15th 70.9%
69.9%	65%	72%	71%	70%	67%	83%	83%	74%	76%	60%	77%	69%	62%	52%	78%	79%	61%	49%	76%	81%	62%
61.3%	57%	65%	62%	66%	57%	61%	66%	68%	65%	55%	55%	66%	49%	70%	54%	52%	59%	65%	73%	71%	51%
79.7%	84%	84%	74%	83%	74%	86%	91%	68%	68%	84%	74%	86%	86%	86%	84%	84%	84%	63%	63%	84%	84%
74.4%	83%	75%	77%	78%	76%	80%	79%	67%	63%	80%	76%	76%	76%	62%	80%	73%	74%	73%	76%	68%	70%
70.5%	69%	69%	69%	70%	69%	69%	73%	81%	70%	70%	69%	69%	69%	69%	81%	69%	70%	69%	69%	69%	68%
68.7%	75%	73%	77%	75%	70%	69%	66%	67%	73%	67%	67%	76%	65%	62%	66%	71%	66%	67%	66%	56%	69%
76.7%	82%	88%	83%	80%	67%	76%	83%	82%	80%	81%	81%	49%	80%	68%	84%	80%	80%	69%	68%	83%	66%
77.3%	81%	78%	79%	75%	86%	48%	75%	74%	74%	100%	77%	64%	76%	77%	74%	75%	79%	84%	83%	82%	82%
86.2%	78%	68%	87%	98%	100%	65%	77%	95%	76%	96%	94%	89%	96%	91%	83%	89%	82%	86%	83%	98%	80%
72.1%	76%	76%	75%	73%	76%	76%	71%	45%	76%	64%	76%	81%	76%	76%	69%	69%	69%	71%	76%	71%	72%
72.5%	76%	81%	82%	83%	67%	71%	83%	78%	73%	63%	81%	78%	58%	66%	82%	77%	62%	37%	71%	77%	76%
74.2%	81%	68%	81%	76%	63%	77%	75%	76%	79%	82%	82%	63%	75%	81%	79%	71%	67%	80%	63%	71%	69%
66.6%	68%	66%	77%	70%	68%	68%	67%	56%	62%	68%	68%	42%	68%	68%	69%	69%	70%	67%	68%	69%	70%
63.2%	65%	61%	64%	66%	55%	68%	64%	70%	68%	65%	64%	68%	68%	68%	64%	66%	54%	51%	66%	55%	57%
83.3%	82%	78%	82%	81%	91%	67%	91%	87%	93%	80%	91%	74%	91%	79%	79%	81%	90%	92%	77%	74%	90%
53.9%	57%	44%	55%	52%	59%	62%	57%	55%	56%	56%	55%	34%	59%	48%	55%	59%	51%	55%	58%	48%	56%
79.9%	70%	92%	86%	86%	68%	69%	68%	53%	85%	79%	92%	76%	68%	67%	93%	86%	86%	90%	89%	94%	81%
66.8%	70%	61%	67%	67%	80%	61%	58%	67%	63%	63%	52%	72%	61%	67%	70%	72%	70%	82%	54%	81%	64%
72.1%	77%	66%	80%	65%	72%	64%	71%	84%	85%	87%	67%	43%	72%	54%	73%	72%	82%	76%	55%	79%	90%
74.2%	86%	74%	74%	85%	68%	70%	83%	86%	72%	69%	57%	65%	65%	72%	75%	86%	87%	73%	74%	65%	72%
64.4%	70%	56%	68%	70%	76%	50%	65%	65%	61%	74%	61%	61%	61%	59%	72%	71%	66%	59%	56%	57%	74%
82.7%	91%	88%	89%	89%	76%	88%	90%	91%	91%	84%	100%	61%	85%	66%	73%	89%	80%	50%	92%	96%	68%
68.2%	69%	70%	72%	69%	62%	69%	72%	69%	68%	66%	72%	67%	67%	79%	65%	67%	59%	67%	73%	67%	63%
78.3%	81%	66%	84%	88%	88%	68%	86%	83%	92%	76%	68%	61%	92%	79%	83%	87%	85%	73%	68%	68%	68%
61.0%	64%	63%	68%	63%	55%	61%	65%	59%	59%	61%	59%	64%	57%	55%	63%	57%	55%	55%	55%	81%	62%
69.8%	81%	68%	75%	75%	77%	62%	72%	73%	69%	66%	62%	60%	61%	72%	70%	68%	70%	74%	68%	66%	76%
72.9%	77%	72%	85%	79%	73%	66%	79%	78%	80%	80%	61%	62%	78%	72%	80%	84%	64%	39%	71%		78%
61.2%	65%	53%	65%	65%	79%	44%	64%	71%	63%	67%	59%	47%	67%	38%	68%	69%	62%	68%	49%	55%	68%
75.1%	75%	84%	85%	90%	70%	66%	81%	78%	74%	70%	67%	67%	67%	67%	80%	80%	65%	78%	90%	67%	77%
57.4%	70%	56%	67%	71%	65%	41%	55%	65%	55%	60%	59%	55%	60%	61%	55%	47%	64%	63%	61%	45%	31%
72.9%	82%	76%	90%	82%	79%	63%	71%	67%	76%	71%	67%	67%	74%	67%	71%	71%	73%	67%	67%	79%	71%
68.8%	65%	65%	70%	65%	77%	77%	70%	70%	77%	66%	70%	63%	66%	63%	66%	66%	66%	63%	77%	77%	66%
72.3%	73%	73%	65%	69%	77%	91%	60%	62%	60%	73%	65%	77%	77%	77%	73%	73%	73%	77%	77%	73%	73%
71.7%	78%	73%	79%	83%	83%	67%	75%	76%	69%	75%	65%	65%	69%	65%	76%	70%	65%	75%	55%	71%	71%
73.4%	72%	68%	76%	74%	47%	62%	81%	82%	83%	81%	65%	81%	80%	45%	78%	82%	79%	80%	74%	70%	81%
73.8%	86%	72%	86%	86%	52%	55%	72%	76%	81%	86%	91%	47%	84%	61%	81%	77%	63%	72%	67%	70%	85%
69.0%	73%	76%	70%	66%	51%	65%	82%	60%	73%	75%	67%	67%	75%	76%	65%	67%	62%	70%	73%		67%
81.4%	88%	89%	85%	85%	91%	81%	82%	81%	88%	83%	93%	69%	88%	69%	88%	83%	68%	72%	69%	86%	72%
67.9%	67%	77%	72%	77%	84%	44%	72%	77%	69%	71%	71%	54%	83%	46%	64%	74%	69%	81%	54%	59%	61%
88.8%	84%	98%	81%	94%	77%	86%	100%	85%	82%	98%	77%	86%	98%	86%	98%	98%	98%	86%	77%	77%	98%
65.2%	75%	57%	70%	67%	79%	34%	67%	68%	74%	70%	83%	34%	75%	47%	67%	68%	72%	73%	44%	75%	71%
64.9%	65%	54%	63%	67%	65%	66%	81%	63%	65%	76%	62%	77%	70%	65%	58%	62%	61%	56%	69%	58%	59%
71.0%	55%	79%	78%	74%	45%	74%	55%	49%	64%	71%	81%	81%	76%	70%	78%	66%	83%	79%	73%	79%	81%

Model Similarity Dendrogram

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