	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 4.1 Fast
Score	2nd 76.5%	4th 75.8%	6th 75.3%	3rd 76.2%	8th 74.4%	21st 67.5%	9th 73.9%	10th 73.4%	11th 73.4%	5th 75.4%	13th 73.0%	16th 72.2%	7th 74.6%	12th 73.1%	20th 67.9%	1st 76.9%	18th 70.8%	17th 71.1%	19th 70.2%	14th 72.5%	15th 72.3%
81.7%	85%	84%	76%	83%	84%	65%	75%	87%	87%	82%	84%	90%	90%	82%	78%	83%	82%	77%	78%	86%	78%
80.5%	91%	86%	89%	90%	73%	75%	79%	86%	73%	90%	69%	84%	85%	75%	92%	85%	69%	69%	78%	78%	75%
57.4%	57%	57%	59%	57%	55%	51%	56%	61%	59%	58%	59%	63%	55%	59%	55%	61%	59%	59%	55%	55%	55%
51.9%	56%	57%	59%	47%	59%	55%	61%	52%	55%	51%	48%	41%	59%	60%	0%	59%	43%	50%	59%	47%	72%
83.1%	71%	76%	69%	76%	82%	89%	74%	86%	82%	95%	89%	89%	85%	85%	74%	88%	82%	94%	89%	96%	74%
72.0%	65%	68%	68%	70%	77%	69%	77%	81%	76%	74%	74%	68%	84%	74%	63%	65%	71%	65%	73%	76%	75%
85.5%	86%	88%	82%	80%	86%	90%	82%	86%	89%	88%	88%	88%	88%	90%	81%	88%	88%	77%	80%	87%	84%
71.9%	72%	69%	67%	68%	73%	66%	72%	85%	82%	72%	69%	81%	69%	73%	65%	82%	66%	85%	66%	69%	59%
87.8%	89%	89%	74%	95%	85%	74%	82%	85%	85%	94%	95%	94%	95%	94%	85%	87%	95%	95%	85%	87%	80%
55.8%	61%	59%	63%	58%	61%	59%	67%	51%	61%	47%	56%	40%	52%	63%	50%	59%	40%	59%	55%	51%	59%
66.4%	73%	74%	77%	77%	64%	71%	55%	72%	60%	71%	71%	56%	68%	59%	73%	71%	50%	46%	68%	67%	72%
43.5%	52%	59%	52%	52%	43%	36%	44%	40%	45%	40%	44%	30%	40%	52%	54%	52%	30%	30%	44%	27%	47%
84.0%	81%	84%	87%	84%	87%	83%	84%	70%	84%	87%	85%	83%	84%	84%	87%	87%	84%	77%	85%	90%	88%
70.2%	71%	72%	70%	71%	72%	74%	72%	69%	72%	73%	68%	67%	72%	67%	70%	70%	76%	64%	66%	69%	70%
78.1%	87%	84%	84%	83%	80%	84%	83%	81%	83%	87%	83%	86%	82%	83%	0%	79%	82%	76%	74%	82%	78%
67.2%	74%	68%	72%	76%	71%	48%	62%	68%	70%	70%	66%	69%	68%	67%	69%	68%	68%	67%	61%	63%	67%
61.6%	73%	77%	77%	77%	73%	59%	55%	61%	68%	62%	61%	59%	59%	61%	0%	77%	63%	50%	57%	59%	65%
60.5%	65%	61%	69%	67%	62%	46%	58%	60%	57%	61%	60%	63%	56%	60%	64%	59%	62%	59%	57%	63%	61%
66.7%	73%	66%	61%	68%	63%	50%	83%	65%	65%	63%	62%	65%	83%	53%	67%	67%	62%	69%	76%	79%	60%
74.8%	80%	71%	83%	75%	77%	82%	75%	75%	73%	79%	73%	79%	76%	72%	81%	75%	69%	71%	64%	68%	73%
82.1%	89%	83%	85%	92%	85%	72%	85%	72%	82%	89%	82%	80%	82%	85%	84%	89%	84%	69%	75%	75%	85%
84.6%	91%	88%	86%	86%	86%	78%	86%	87%	83%	87%	86%	83%	86%	86%	85%	84%	80%	86%	75%	80%	87%
66.4%	73%	67%	72%	64%	67%	58%	71%	64%	71%	72%	66%	59%	61%	68%	71%	69%	69%	55%	68%	64%	66%
69.0%	75%	73%	78%	70%	69%	69%	73%	71%	68%	70%	72%	61%	69%	68%	73%	69%	68%	55%	62%	68%	69%
85.3%	89%	82%	90%	90%	90%	84%	86%	82%	80%	83%	87%	75%	85%	89%	92%	89%	83%	85%	82%	84%	85%
78.8%	87%	79%	81%	79%	81%	67%	74%	73%	75%	84%	85%	79%	76%	81%	82%	86%	77%	72%	81%	76%	80%
75.9%	82%	78%	77%	86%	77%	59%	71%	77%	74%	81%	74%	80%	76%	69%	80%	82%	65%	74%	71%	82%	78%
82.9%	89%	86%	69%	89%	89%	61%	82%	83%	91%	86%	73%	85%	86%	73%	95%	91%	80%	91%	73%	81%	88%
45.5%	45%	62%	46%	56%	53%	37%	46%	42%	34%	39%	40%	19%	40%	46%	55%	52%	50%	50%	34%	56%	54%
54.8%	51%	48%	57%	62%	66%	44%	47%	52%	55%	52%	52%	61%	46%	58%	57%	53%	56%	69%	58%	59%	48%
85.4%	89%	89%	88%	86%	87%	73%	89%	75%	87%	91%	87%	89%	84%	87%	89%	91%	87%	75%	80%		85%
80.0%	80%	80%	78%	80%	83%	87%	81%	76%	78%	79%	78%	74%	83%	78%	83%	76%	78%	78%	83%	83%	83%
85.3%	84%	85%	87%	85%	83%	78%	84%	89%	87%	86%	87%	91%	83%	87%	87%	88%	84%	87%	83%	83%	83%
69.7%	77%	67%	77%	75%	75%	64%	71%	71%	70%	76%	66%	71%	70%	64%	74%	73%	66%	70%	55%	71%	61%
71.7%	78%	82%	79%	71%	53%	57%	79%	69%	66%	83%	74%	61%	79%	75%	63%	81%	61%	79%	83%	70%	62%
80.7%	81%	81%	90%	77%	69%	79%	89%	89%	76%	83%	84%	81%	84%	79%	76%	82%	81%	78%	72%	76%	87%
74.4%	80%	80%	71%	81%	73%	71%	73%	78%	77%	74%	70%	83%	74%	70%	80%	85%	68%	70%	66%	73%	66%
89.2%	82%	97%	94%	92%	95%	94%	100%	90%	100%	93%	86%	81%	100%	78%	85%	92%	81%	81%	83%	83%	87%
66.9%	73%	71%	71%	76%	71%	59%	72%	68%	66%	71%	60%	70%	69%	60%	73%	72%	58%	64%	57%	65%	59%
93.9%	96%	94%	96%	94%	91%	87%	93%	98%	96%	95%	96%	100%	91%	96%	91%	97%	94%	96%	91%	91%	88%
71.1%	77%	74%	74%	77%	74%	57%	75%	76%	63%	77%	68%	64%	75%	68%	71%	72%	76%	74%	67%	61%	73%
65.2%	67%	70%	62%	62%	62%	52%	70%	63%	59%	57%	75%	71%	70%	75%	67%	70%	65%	69%	59%	69%	55%
86.7%	91%	94%	91%	91%	93%	91%	84%	91%	91%	89%	86%	91%	89%	91%	0%	100%	91%	91%	91%	95%	89%

Model Similarity Dendrogram

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