	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	6th 75.5%	10th 73.7%	3rd 76.6%	2nd 76.8%	9th 74.5%	18th 70.7%	12th 73.5%	8th 74.8%	5th 76.1%	7th 75.0%	11th 73.7%	20th 69.7%	13th 73.0%	19th 69.9%	1st 76.8%	4th 76.2%	16th 72.3%	21st 69.5%	17th 70.7%	15th 72.6%	14th 72.9%
60.9%	61%	63%	61%	62%	62%	62%	67%	58%	65%	64%	64%	55%	55%	59%	60%	60%	60%	51%	65%	65%	59%
55.9%	43%	62%	56%	54%	52%	75%	53%	45%	50%	63%	50%	81%	53%	73%	64%	53%	44%	48%	54%	58%	43%
56.6%	59%	59%	46%	60%	54%	54%	94%	47%	54%	59%	54%	54%	54%	54%	59%	59%	59%	54%	37%	59%	59%
73.6%	77%	73%	76%	73%	78%	70%	75%	75%	81%	78%	68%	68%	76%	67%	80%	74%	75%	67%	74%	67%	73%
65.2%	64%	63%	64%	68%	68%	58%	79%	70%	67%	72%	58%	58%	66%	58%	75%	74%	60%	58%	58%	58%	73%
82.4%	84%	77%	70%	75%	83%	99%	81%	86%	87%	85%	86%	79%	89%	96%	74%	77%	84%	81%	84%	81%	73%
79.5%	87%	73%	81%	88%	84%	73%	75%	89%	74%	75%	72%	92%	70%	68%	92%	91%	71%	92%	66%	67%	89%
72.8%	75%	76%	79%	81%	81%	58%	72%	78%	72%	81%	75%	63%	64%	71%	78%	76%	73%	62%	71%	67%	75%
79.4%	59%	66%	78%	85%	96%	89%	88%	90%	97%	71%	82%	87%	81%	71%	69%	74%	79%	65%	89%	84%	67%
70.0%	68%	68%	75%	80%	68%	68%	65%	68%	68%	71%	68%	81%	68%	68%	71%	74%	63%	62%	68%	68%	79%
72.9%	78%	76%	84%	83%	76%	82%	76%	84%	70%	61%	67%	84%	62%	54%	78%	78%	50%	47%	88%	86%	67%
85.6%	90%	84%	93%	94%	88%	83%	81%	86%	91%	82%	84%	80%	83%	85%	94%	83%	80%	84%	80%		87%
76.1%	83%	81%	83%	83%	79%	70%	76%	75%	75%	74%	72%	64%	74%	65%	83%	79%	77%	84%	65%	77%	79%
84.0%	88%	82%	84%	82%	88%	79%	82%	85%	88%	86%	86%	66%	86%	88%	83%	84%	88%	85%	88%	88%	79%
84.6%	80%	85%	80%	80%	85%	81%	88%	97%	87%	87%	85%	77%	85%	85%	80%	81%	89%	84%	85%	87%	88%
83.4%	84%	80%	89%	89%	85%	79%	90%	88%	89%	90%	90%	68%	89%	83%	81%	80%	80%	80%	87%	65%	85%
54.7%	55%	53%	65%	59%	61%	52%	47%	40%	47%	56%	61%	51%	45%	50%	60%	66%	52%	60%	61%	51%	57%
81.9%	88%	80%	84%	84%	89%	73%	82%	92%	83%	72%	90%	75%	87%	84%	80%	90%	82%	63%	69%	93%	79%
59.0%	60%	57%	54%	53%	82%	46%	50%	54%	58%	68%	52%	46%	56%	52%	82%	84%	61%	58%	35%	72%	60%
79.6%	83%	72%	80%	79%	82%	78%	83%	86%	86%	77%	76%	70%	84%	80%	71%	82%	87%	82%	80%	82%	71%
78.0%	81%	80%	81%	84%	78%	79%	77%	78%	78%	78%	81%	70%	76%	75%	79%	81%	78%	78%	72%	74%	79%
74.9%	80%	79%	82%	77%	72%	83%	75%	71%	72%	75%	79%	70%	74%	73%	79%	78%	77%	59%	73%	70%	75%
66.6%	62%	67%	61%	64%	71%	69%	68%	76%	69%	75%	71%	53%	73%	52%	68%	66%	75%	69%	71%	53%	66%
68.2%	71%	64%	70%	70%	67%	65%	72%	72%	69%	71%	65%	65%	65%	65%	63%	69%	69%	65%	73%	65%	78%
87.7%	92%	92%	86%	87%	88%	90%	77%	94%	94%	93%	92%	69%	91%	83%	88%	89%	92%	89%	94%	91%	71%
78.0%	70%	87%	85%	82%	76%	64%	84%	68%	70%	82%	87%	81%	70%	69%	87%	83%	64%	84%	90%	75%	79%
74.8%	82%	71%	80%	81%	80%	68%	74%	78%	75%	74%	71%	64%	78%	77%	79%	68%	81%	71%	69%	74%	75%
76.7%	82%	73%	85%	81%	77%	71%	75%	72%	81%	77%	76%	68%	80%	73%	80%	85%	77%	78%	74%	74%	72%
62.2%	66%	76%	73%	74%	55%	64%	73%	55%	54%	55%	53%	53%	55%	53%	67%	69%	57%	66%	68%	65%	56%
69.9%	80%	65%	79%	79%	80%	56%	75%	72%	71%	70%	69%	65%	73%	68%	76%	73%	64%	54%	68%	67%	64%
77.7%	77%	77%	78%	80%	76%	75%	79%	75%	76%	77%	73%	78%	78%	78%	81%	81%	82%	77%	79%	73%	81%
61.0%	56%	56%	63%	62%	37%	42%	81%	71%	81%	56%	81%	81%	42%	81%	56%	56%	57%	42%	42%	81%	56%
55.0%	64%	58%	50%	50%	58%	58%	10%	63%	58%	64%	58%	58%	58%	42%	64%	64%	57%	58%	42%	58%	64%
71.9%	81%	60%	76%	79%	71%	66%	65%	69%	73%	73%	68%	71%	68%	68%	88%	79%	76%	78%	60%	69%	71%
78.3%	92%	88%	90%	87%	50%	78%	71%	77%	77%	72%	72%	72%	82%	71%	85%	91%	81%	74%	73%	75%	87%
76.3%	81%	83%	76%	77%	71%	65%	78%	76%	78%	77%	77%	78%	82%	72%	76%	68%	83%	78%	70%	78%	78%
81.7%	82%	81%	79%	81%	85%	83%	84%	73%	87%	79%	78%	78%	85%	78%	83%	84%	83%	78%	89%	80%	85%
74.7%	81%	77%	87%	85%	81%	75%	81%	70%	82%	83%	77%	58%	74%	58%	83%	74%	53%	69%	58%	78%	84%
81.0%	82%	83%	87%	85%	86%	79%	83%	79%	80%	80%	89%	75%	82%	84%	79%	83%	76%	79%	74%	81%	74%
76.7%	82%	89%	90%	70%	54%	81%	10%	98%	97%	82%	81%	93%	82%	58%	82%	82%	82%	54%	81%	81%	82%
73.1%	79%	73%	74%	79%	92%	46%	80%	79%	81%	77%	84%	40%	81%	44%	78%	78%	88%	81%	53%	81%	68%
83.7%	80%	86%	86%	86%	84%	65%	91%	88%	84%	85%	84%	95%	88%	96%	90%	79%	85%	66%	82%	69%	88%
77.2%		75%	92%	90%	73%	88%	95%	68%	95%	100%	61%	61%	74%	77%	77%	79%	60%	74%	83%	61%	61%

Model Similarity Dendrogram

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