	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	1st 80.2%	4th 78.8%	2nd 79.1%	15th 73.3%	6th 78.7%	21st 67.4%	13th 73.9%	10th 75.3%	11th 75.0%	3rd 79.0%	9th 75.6%	14th 73.8%	8th 77.5%	19th 72.9%	7th 77.7%	4th 78.8%	12th 74.2%	17th 73.3%	15th 73.3%	20th 71.3%	18th 73.3%
79.6%	87%	85%	81%	90%	89%	54%	73%	81%	73%	83%	73%	81%	81%	73%	86%	85%	85%	78%	72%	83%	78%
73.8%	71%	68%	74%	79%	46%	92%	71%	78%	63%	78%	93%	91%	84%	93%	64%	61%	76%	59%	89%	62%	58%
65.5%	76%	62%	76%	0%	68%	68%	66%	68%	60%	75%	72%	72%	72%	68%	72%	65%	60%	60%	58%	60%	97%
82.9%	86%	80%	81%	84%	81%	77%	84%	86%	86%	82%	83%	79%	86%	84%	86%	86%	81%	82%	88%	79%	79%
80.6%	80%	85%	80%	87%	81%	72%	80%	80%	77%	87%	82%	80%	82%	78%	80%	80%	78%	81%	80%	78%	85%
79.0%	81%	81%	73%	84%	81%	86%	77%	92%	81%	81%	74%	76%	79%	76%	75%	77%	77%	79%	77%	71%	82%
88.5%	89%	90%	85%	89%	92%	87%	87%	90%	91%	94%	89%	82%	92%	93%	89%	94%	83%	95%	83%	83%	81%
62.2%	67%	61%	66%	75%	63%	34%	61%	65%	65%	72%	55%	62%	65%	53%	69%	69%	63%	62%	54%	62%	64%
81.0%	81%	87%	78%	81%	86%	52%	66%	83%	64%	90%	84%	81%	83%	81%	83%	92%	90%	95%	71%	86%	86%
79.8%	81%	84%	81%	82%	79%	87%	74%	68%	79%	83%	73%	84%	81%	79%	83%	83%	76%	77%	79%	79%	83%
81.0%	91%	91%	91%	90%	82%	82%	84%	76%	83%	80%	88%	84%	82%	81%	81%	75%	75%	66%	77%	82%	61%
79.6%	91%	84%	86%	83%	86%	74%	76%	83%	84%	74%	75%	83%	70%	78%	88%	83%	65%	72%	86%	66%	84%
81.6%	86%	81%	89%	94%	86%	63%	87%	87%	85%	87%	83%	80%	83%	75%	81%	83%	81%	72%	69%	81%	81%
79.7%	91%	82%	83%	82%	90%	79%	89%	82%	86%	80%	80%	76%	84%	66%	83%	84%	69%	69%	82%	80%	57%
86.1%	94%	88%	84%	86%	93%	86%	90%	89%	91%	90%	87%	85%	91%	87%	76%	85%	85%	78%	89%	80%	74%
71.0%	78%	76%	81%	83%	71%	51%	66%	76%	72%	72%	64%	63%	79%	66%	78%	74%	83%	73%	67%	60%	58%
59.5%	67%	74%	77%	65%	63%	48%	58%	41%	58%	60%	60%	42%	60%	55%	66%	71%	57%	43%	63%	50%	72%
65.6%	81%	68%	78%	79%	74%	40%	55%	72%	61%	69%	54%	61%	70%	54%	70%	74%	74%	47%	62%	73%	61%
52.4%	56%	49%	56%	46%	61%	40%	54%	53%	56%	60%	53%	39%	66%	47%	61%	68%	53%	46%	41%	46%	49%
76.9%	88%	82%	81%	80%	83%	70%	76%	70%	72%	85%	76%	70%	75%	70%	83%	83%	72%	68%	82%	74%	74%
81.2%	86%	88%	86%	86%	93%	46%	91%	93%	76%	86%	84%	75%	81%	73%	79%	94%	80%	84%	65%	75%	84%
78.4%	91%	82%	80%	91%	90%	52%	80%	85%	78%	91%	60%	73%	82%	73%	84%	84%	86%	77%	62%	66%	80%
77.9%	76%	78%	82%	80%	80%	79%	79%	78%	80%	81%	80%	66%	67%	70%	85%	79%	73%	88%	82%	80%	73%
79.5%	81%	76%	84%	74%	82%	72%	84%	79%	84%	84%	85%	80%	82%	82%	81%	81%	81%	62%	74%	81%	81%
77.0%	69%	77%	76%	71%	81%	81%	79%	81%	81%	79%	82%	79%	75%	71%	74%	78%	81%	87%	80%	76%	58%
70.0%	76%	70%	76%	72%	74%	58%	66%	71%	73%	75%	67%	64%	75%	73%	69%	80%	67%	70%	70%	68%	56%
81.4%	88%	89%	92%	84%	92%	54%	76%	85%	82%	87%	62%	84%	84%	73%	91%	87%	82%	82%	78%	81%	77%
70.0%	74%	76%	69%	80%	84%	50%	73%	83%	78%	76%	66%	62%	69%	55%	87%	76%	68%	63%	59%	52%	70%
78.6%	85%	87%	89%	100%	82%	67%	79%	70%	76%	76%	71%	71%	72%	69%	88%	81%	72%	71%	73%	84%	88%
74.8%	85%	78%	79%	85%	82%	57%	63%	76%	83%	78%	90%	60%	87%	75%	76%	83%	64%	81%	74%	49%	66%
66.8%	55%	70%	63%	47%	68%	88%	64%	70%	74%	64%	87%	88%	66%	82%	42%	53%	53%	79%	80%	66%	43%
73.9%	69%	83%	69%	0%	78%	78%	80%	77%	86%	70%	73%	73%	73%	78%	80%	80%	86%	86%	88%	50%	95%
63.6%	76%	62%	76%	0%	68%	68%	66%	68%	60%	75%	72%	72%	72%	68%	66%	65%	60%	60%	58%	52%	71%
74.6%	78%	73%	78%	78%	82%	67%	70%	71%	76%	76%	70%	70%	76%	71%	77%	80%	78%	76%	67%	76%	77%
59.6%	75%	74%	57%	83%	58%	56%	46%	38%	51%	56%	54%	59%	50%	49%	63%	71%	54%	60%	73%	57%	67%
75.6%	79%	79%	81%	82%	77%	64%	76%	79%	75%	85%	76%	68%	80%	68%	82%	77%	80%	68%	66%	72%	74%
81.9%	85%	87%	83%	70%	89%	90%	82%	68%	87%	78%	89%	90%	89%	89%	62%	79%	90%	84%	86%	81%	62%
83.2%	73%	86%	84%	97%	80%	73%	71%	82%	82%	87%	86%	93%	84%	86%	92%	87%	82%	88%	91%	89%	54%
70.7%	81%	77%	73%	81%	78%	52%	72%	80%	69%	83%	62%	52%	75%	56%	81%	82%	62%	74%	54%	61%	80%
80.6%	94%	79%	94%	0%	85%	85%	83%	85%	76%	93%	90%	90%	90%	85%	83%	82%	76%	76%	74%	85%	88%
76.2%	80%	79%	77%	77%	74%	80%	80%	76%	76%	83%	77%	72%	80%	72%	82%	76%	71%	61%	72%	76%	79%
80.9%	81%	88%	80%	85%	82%	66%	77%	82%	75%	82%	84%	83%	78%	83%	85%	82%	74%	85%	78%	85%	83%
77.5%	90%	91%	91%	91%	71%	74%	66%	42%	59%	72%	86%	79%	81%	76%	77%	78%	86%	87%	80%	69%	81%

Model Similarity Dendrogram

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