	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	3rd 76.5%	4th 76.3%	1st 78.3%	15th 71.6%	18th 70.2%	16th 71.4%	2nd 76.9%	5th 76.2%	6th 76.0%	10th 74.0%	9th 74.1%	17th 70.8%	8th 74.3%	14th 72.0%	13th 72.8%	12th 73.0%	19th 69.7%	21st 67.4%	7th 74.3%	20th 68.7%	11th 73.5%
80.3%	81%	81%	88%	80%	67%	63%	89%	89%	85%	85%	79%	76%	85%	86%	90%	84%	73%	64%	75%	77%	89%
69.3%	68%	57%	74%	79%	48%	66%	72%	73%	57%	70%	82%	82%	71%	79%	73%	78%	65%	56%	80%	49%	77%
83.1%	89%	86%	90%	93%	67%	83%	83%	79%	67%	93%	83%	93%	84%	80%	86%	86%	74%	84%	79%	80%	86%
86.3%	88%	85%	90%	86%	88%	84%	88%	81%	88%	87%	86%	88%	87%	85%	88%	86%	86%	81%	86%	88%	87%
87.8%	94%	88%	91%	96%	88%	93%	96%	89%	89%	94%	82%	88%	87%	81%	88%	76%	88%	79%	84%		84%
79.3%	78%	80%	77%	83%	79%	82%	80%	90%	81%	79%	86%	69%	79%	77%	74%	77%	83%	83%	70%	71%	88%
83.7%	84%	85%	84%	84%	85%	85%	82%	85%	85%	85%	81%	83%	78%	82%	89%	86%	84%	84%	79%		84%
71.3%	85%	79%	78%	81%	83%	53%	69%	75%	71%	83%	68%	61%	73%	63%	78%	77%	60%	61%	55%	67%	78%
76.6%	67%	79%	65%	65%	87%	76%	92%	85%	87%	70%	78%	81%	79%	81%	64%	70%	81%	73%	76%	86%	66%
86.4%	88%	84%	88%	91%	88%	88%	83%	85%	88%	87%	84%	85%	88%	88%	83%	87%	87%	80%	88%	88%	87%
66.1%	76%	72%	68%	62%	61%	85%	65%	86%	67%	51%	64%	69%	57%	49%	56%	51%	56%	54%	87%	68%	85%
84.1%	88%	86%	90%	86%	85%	79%	83%	88%	86%	85%	83%	84%	82%	78%	87%	86%	78%	74%	86%	89%	84%
58.6%	44%	66%	63%	53%	74%	81%	64%	49%	73%	48%	75%	58%	61%	80%	43%	51%	39%	43%	79%	43%	43%
79.0%	89%	84%	83%	83%	85%	65%	91%	82%	83%	82%	82%	71%	85%	62%	74%	79%	68%	72%	89%	83%	67%
73.0%	75%	83%	81%	73%	77%	68%	83%	85%	73%	76%	67%	78%	81%	64%	65%	75%	74%	76%	66%	51%	62%
71.2%	75%	70%	75%	70%	66%	64%	87%	78%	75%	72%	75%	69%	75%	74%	68%	72%	75%	37%	75%	59%	85%
73.5%	89%	89%	89%	82%	72%	59%	74%	64%	73%	76%	74%	43%	77%	65%	87%	75%	61%	53%	77%	78%	87%
73.9%	84%	78%	81%	81%	82%	47%	71%	81%	71%	79%	63%	64%	78%	59%	81%	75%	77%	66%	69%	82%	82%
54.8%	54%	49%	53%	52%	56%	36%	54%	64%	60%	65%	55%	47%	61%	53%	60%	65%	72%	41%	47%	57%	50%
85.9%	91%	88%	94%	94%	84%	78%	87%	92%	78%	90%	83%	81%	92%	82%	94%	92%	76%	83%	85%	80%	80%
63.6%	61%	68%	67%	58%	61%	60%	76%	61%	78%	64%	73%	68%	60%	75%	51%	60%	56%	46%	60%	67%	65%
74.1%	75%	81%	88%	73%	83%	73%	86%	89%	88%	68%	76%	74%	80%	75%	71%	53%	60%	70%	63%	71%	59%
75.9%	88%	74%	89%	86%	65%	66%	73%	71%	86%	75%	76%	38%	51%	62%	87%	84%	86%	89%	70%	86%	92%
63.7%	59%	73%	68%	57%	74%	88%	67%	51%	74%	61%	81%	51%	61%	76%	50%	56%	51%	58%	79%	51%	51%
74.5%	78%	67%	84%	84%	77%	68%	83%	78%	84%	72%	81%	68%	76%	62%	72%	67%	65%	72%	81%	78%	68%
67.6%	66%	71%	70%	63%	67%	66%	69%	66%	71%	66%	71%	72%	68%	74%	71%	69%	56%	67%	71%	64%	62%
68.0%	83%	76%	79%	79%	78%	42%	61%	79%	62%	76%	39%	58%	75%	52%	77%	78%	69%	62%	55%	72%	76%
68.6%	73%	79%	80%	80%	40%	63%	79%	79%	66%	75%	72%	67%	75%	65%	69%	68%	68%	58%	64%	52%	69%
86.0%	91%	91%	95%	95%	89%	86%	87%	85%	83%	81%	82%	77%	85%	69%	89%	90%	84%	89%	89%		82%
79.7%	85%	82%	87%	85%	73%	87%	76%	83%	84%	84%	80%	65%	74%	75%	84%	85%	79%	74%	82%	66%	83%
68.8%	65%	75%	80%	67%	50%	80%	80%	87%	85%	64%	79%	81%	71%	75%	58%	49%	62%	62%	71%	51%	52%
62.3%	59%	65%	59%	0%	81%	65%	65%	69%	81%	56%	65%	56%	64%	68%	69%	69%	64%	64%	69%	62%	58%
69.3%	79%	73%	80%	0%	58%	73%	73%	70%	58%	83%	73%	83%	75%	70%	76%	70%	75%	75%	70%	65%	77%
83.2%	89%	85%	86%	89%	86%	78%	73%	84%	83%	85%	78%	80%	81%	80%	87%	89%	85%	84%	79%	80%	86%
51.8%	58%	72%	53%	68%	23%	50%	42%	47%	44%	44%	45%	55%	42%	44%	56%	54%	51%	46%	81%	59%	54%
56.3%	52%	56%	57%	56%	21%	64%	59%	59%	51%	55%	58%	71%	51%	71%	46%	60%	50%	60%	68%	60%	58%
60.6%	61%	59%	63%	55%	35%	85%	77%	63%	75%	49%	77%	70%	68%	83%	41%	39%	45%	59%	65%	60%	44%
82.6%	90%	90%	93%	77%	98%	86%	95%	87%	96%	81%	80%	74%	94%	76%	80%	86%	74%	55%	78%	51%	93%
69.7%	78%	73%	80%	75%	55%	64%	81%	76%	78%	77%	66%	70%	77%	65%	64%	64%	57%	61%	61%	68%	73%
66.6%	65%	69%	63%	0%	85%	69%	69%	73%	85%	60%	69%	60%	68%	72%	71%	73%	68%	68%	73%	71%	67%
66.6%	75%	65%	76%	78%	36%	81%	73%	67%	58%	70%	71%	69%	75%	62%	60%	77%	58%	63%	67%	49%	69%
88.2%	96%	93%	92%	94%	82%	65%	87%	96%	76%	94%	90%	89%	84%	91%	91%	89%	93%	90%	88%	85%	88%
79.4%	78%	74%	74%	85%	79%	78%	82%	57%	84%	84%	75%	78%	78%	85%	82%	80%	84%	83%	79%	84%	84%

Model Similarity Dendrogram

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