	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 76.2%	6th 76.0%	2nd 77.5%	1st 77.7%	15th 73.2%	17th 71.5%	9th 75.3%	13th 74.3%	8th 75.4%	10th 75.2%	3rd 77.0%	16th 72.4%	14th 73.9%	12th 74.3%	7th 75.8%	4th 76.7%	19th 70.3%	21st 67.1%	11th 74.5%	18th 71.5%	20th 70.1%
81.0%	83%	82%	79%	87%	61%	73%	80%	83%	86%	79%	86%	90%	83%	86%	81%	89%	81%	73%	80%	83%	77%
71.4%	70%	63%	73%	76%	25%	76%	67%	69%	61%	75%	82%	81%	82%	75%	76%	76%	80%	77%	82%	67%	66%
49.7%	55%	50%	55%	44%	44%	57%	54%	47%	44%	54%	59%	44%	44%	55%	47%	47%	50%	48%	47%	54%	44%
80.2%	81%	81%	80%	82%	81%	79%	80%	81%	81%	80%	79%	86%	74%	80%	86%	81%	78%	82%	72%	86%	74%
86.6%	81%	91%	84%	87%	80%	76%	87%	95%	95%	95%	87%	82%	95%	88%	79%	87%	91%	88%	81%	94%	76%
84.4%	80%	85%	79%	91%	91%	91%	88%	94%	90%	84%	80%	77%	94%	83%	77%	82%	91%	81%	84%	67%	84%
86.6%	87%	92%	84%	90%	84%	88%	82%	91%	93%	86%	86%	80%	84%	84%	90%	92%	82%	90%	86%	84%	83%
73.3%	79%	78%	73%	77%	75%	51%	80%	74%	81%	79%	75%	74%	77%	73%	78%	82%	68%	51%	57%	78%	79%
73.0%	76%	69%	69%	70%	79%	56%	66%	66%	70%	77%	80%	71%	71%	76%	76%	71%	82%	81%	68%	80%	80%
84.3%	87%	79%	82%	90%	86%	86%	85%	78%	88%	92%	83%	78%	88%	86%	88%	84%	70%	80%	86%	86%	88%
71.2%	84%	73%	79%	79%	79%	95%	73%	85%	70%	67%	76%	74%	49%	60%	73%	58%	58%	65%	84%	80%	34%
67.0%	76%	73%	73%	77%	70%	66%	69%	68%	73%	53%	73%	68%	49%	66%	73%	68%	42%	54%	73%	67%	75%
69.5%	62%	74%	79%	77%	83%	83%	68%	67%	77%	74%	72%	58%	83%	72%	64%	72%	53%	61%	74%	53%	53%
76.5%	74%	80%	74%	76%	78%	69%	83%	81%	82%	80%	76%	70%	80%	70%	78%	81%	72%	74%	79%	80%	69%
76.4%	76%	71%	80%	82%	77%	74%	82%	74%	75%	78%	82%	70%	77%	79%	78%	76%	70%	77%	72%	73%	81%
79.0%	82%	72%	83%	83%	66%	79%	81%	81%	79%	86%	88%	92%	80%	83%	78%	78%	78%	69%	87%	64%	70%
79.3%	81%	74%	84%	84%	85%	75%	74%	85%	84%	83%	87%	76%	67%	77%	84%	84%	70%	72%	82%	75%	82%
64.6%	72%	67%	69%	68%	83%	44%	67%	71%	59%	61%	63%	59%	67%	54%	68%	66%	56%	51%	67%	70%	74%
47.8%	49%	41%	53%	45%	57%	26%	44%	53%	61%	59%	41%	35%	57%	53%	64%	62%	50%	33%	34%		39%
73.7%	79%	80%	79%	78%	84%	67%	78%	75%	67%	79%	66%	67%	73%	66%	73%	78%	69%	65%	71%	71%	82%
72.3%	75%	75%	84%	83%	78%	67%	81%	68%	76%	82%	78%	68%	75%	73%	70%	77%	58%	60%	58%	72%	60%
71.7%	72%	77%	77%	73%	81%	70%	75%	78%	71%	80%	65%	74%	74%	67%	81%	75%	64%	61%	56%	70%	64%
61.0%	62%	63%	54%	58%	74%	75%	67%	65%	54%	67%	56%	64%	63%	74%	51%	55%	49%	55%	64%	60%	51%
67.8%	64%	75%	83%	77%	73%	80%	64%	70%	67%	70%	78%	56%	70%	74%	78%	67%	56%	48%	77%	48%	48%
81.0%	81%	87%	78%	84%	88%	76%	88%	84%	86%	84%	82%	68%	81%	78%	74%	85%	84%	79%	89%	74%	70%
73.9%	69%	79%	83%	84%	75%	77%	80%	69%	75%	76%	86%	75%	73%	67%	69%	70%	72%	60%	79%	74%	59%
69.3%	79%	74%	73%	75%	80%	51%	72%	70%	67%	69%	51%	70%	72%	59%	79%	75%	67%	77%	61%	62%	73%
72.1%	74%	76%	74%	72%	69%	52%	76%	79%	80%	66%	74%	68%	76%	73%	68%	77%	77%	78%	69%	67%	70%
67.1%	74%	75%	87%	74%	85%	59%	82%	69%	75%	49%	66%	63%	50%	51%	65%	72%	49%	44%	86%	66%	69%
73.2%	77%	84%	77%	80%	68%	68%	58%	77%	80%	69%	82%	71%	70%	71%	78%	81%	74%	41%	78%	80%	73%
72.7%	74%	71%	73%	73%	47%	77%	71%	76%	80%	72%	81%	72%	76%	81%	72%	79%	72%	55%	84%	71%	70%
92.0%	91%	95%	89%	98%	98%	86%	91%	98%	98%	91%	85%	98%	98%	89%	91%	98%	95%	98%	98%	62%	86%
61.8%	67%	62%	67%	55%	55%	70%	66%	59%	55%	66%	71%	55%	55%	67%	66%	59%	62%	59%	59%	52%	70%
70.3%	77%	65%	73%	80%	73%	59%	63%	67%	70%	70%	67%	67%	67%	70%	77%	77%	78%	71%	61%	67%	77%
71.5%	83%	87%	83%	85%	40%	65%	71%	62%	76%	59%	82%	72%	62%	62%	82%	69%	83%	71%	80%	67%	60%
64.0%	67%	63%	72%	75%	60%	72%	63%	60%	52%	73%	64%	61%	72%	58%	71%	69%	60%	51%	58%	70%	53%
80.5%	84%	73%	85%	78%	78%	85%	85%	65%	81%	80%	90%	81%	83%	94%	75%	94%	63%	81%	88%	66%	81%
82.0%	79%	88%	90%	90%	94%	87%	83%	83%	90%	85%	86%	75%	86%	88%	79%	84%	66%	71%	83%	56%	79%
81.3%	80%	83%	89%	92%	61%	84%	82%	84%	88%	87%	95%	90%	90%	86%	83%	88%	67%	64%	74%	77%	63%
93.7%	98%	96%	98%	89%	89%	96%	100%	92%	89%	100%	94%	89%	89%	98%	93%	92%	96%	93%	92%	96%	89%
71.5%	76%	75%	78%	73%	59%	71%	75%	71%	70%	78%	75%	73%	80%	78%	78%	73%	75%	25%	80%	73%	66%
79.8%	88%	88%	79%	79%	83%	60%	86%	75%	75%	78%	88%	80%	62%	84%	88%	84%	88%	80%	79%	68%	83%
79.2%	72%	84%	74%	73%	72%	78%	72%	54%	73%	63%	93%	91%	80%	85%	82%	85%	77%	90%	83%	91%	91%

Model Similarity Dendrogram

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