	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 76.1%	8th 75.3%	1st 77.5%	2nd 77.2%	12th 74.2%	6th 75.7%	9th 74.9%	20th 70.9%	13th 74.1%	10th 74.7%	3rd 77.1%	18th 71.2%	15th 73.7%	14th 74.1%	4th 76.6%	7th 75.7%	17th 71.4%	21st 70.3%	11th 74.6%	19th 71.2%	16th 71.5%
68.5%	62%	66%	77%	67%	63%	74%	73%	62%	70%	72%	69%	66%	65%	76%	64%	66%	64%	73%	67%	72%	71%
52.3%	46%	52%	51%	54%	52%	60%	43%	41%	39%	50%	57%	63%	54%	56%	61%	47%	55%	37%	54%		74%
57.7%	63%	60%	63%	61%	51%	60%	55%	63%	51%	63%	63%	59%	60%	60%	57%	56%	52%	58%	53%	51%	52%
74.1%	79%	76%	76%	69%	75%	70%	73%	75%	81%	71%	78%	60%	71%	78%	81%	80%	72%	77%	70%	75%	69%
74.9%	77%	75%	80%	80%	67%	79%	78%	74%	73%	72%	80%	78%	70%	77%	81%	81%	68%	67%	80%	55%	80%
83.4%	82%	77%	74%	78%	71%	83%	85%	74%	90%	87%	83%	91%	90%	96%	81%	70%	90%	90%	88%	87%	85%
81.3%	86%	78%	87%	88%	85%	73%	83%	88%	83%	77%	83%	78%	84%	74%	73%	86%	80%	80%	84%	87%	71%
89.7%	87%	93%	84%	90%	97%	72%	90%	87%	92%	86%	97%	98%	90%	91%	90%	92%	93%	78%	91%	88%	98%
84.3%	84%	80%	91%	90%	95%	93%	97%	84%	91%	84%	76%	87%	84%	91%	72%	71%	81%	86%	86%	79%	69%
69.1%	76%	73%	68%	69%	71%	77%	66%	63%	71%	68%	70%	68%	65%	67%	69%	64%	63%	67%	76%		71%
76.8%	83%	84%	85%	86%	74%	95%	74%	88%	78%	69%	79%	82%	68%	61%	81%	77%	65%	57%	78%	73%	76%
86.8%	87%	83%	97%	92%	90%	85%	87%	94%	89%	80%	84%	80%	86%	85%	93%	89%	67%	93%	84%	90%	87%
65.3%	65%	69%	72%	72%	70%	86%	64%	57%	59%	65%	78%	60%	64%	66%	72%	64%	61%	49%	73%	64%	41%
75.4%	78%	82%	79%	79%	78%	71%	78%	68%	75%	67%	78%	72%	78%	80%	82%	76%	69%	82%	78%	67%	66%
82.0%	90%	89%	85%	87%	80%	90%	82%	72%	79%	91%	87%	71%	87%	82%	86%	84%	82%	75%	84%	56%	82%
86.2%	87%	89%	87%	81%	79%	80%	88%	90%	84%	97%	88%	85%	87%	88%	93%	87%	76%	88%	87%	74%	95%
55.7%	66%	62%		65%	61%	54%	60%	48%	53%	47%	63%	61%	44%	54%		68%	41%	60%	55%	52%	44%
81.4%	90%	84%	85%	90%	87%	64%	73%	84%	84%	78%	76%	81%	87%	75%	85%	88%	81%	72%	85%	79%	81%
44.0%	52%	31%	51%	49%	61%	37%	43%	41%	41%	56%	52%	12%	44%	31%	62%	63%	33%	42%	28%	53%	43%
78.4%	78%	80%	74%	74%	84%	71%	83%	75%	82%	73%	81%	69%	82%	86%	73%	81%	88%	90%	77%	72%	73%
66.2%	65%	65%	70%	67%	69%	75%	63%	53%	65%	65%	73%	60%	69%	69%	61%	68%	64%	72%	79%	67%	51%
59.2%	57%	60%	58%	59%	55%	79%	55%	45%	58%	61%	69%	47%	60%	62%	62%	59%	63%	57%	71%	67%	40%
66.8%	58%	63%	63%	62%	69%	72%	64%	75%	66%	64%	71%	53%	69%	75%	74%	71%	70%	63%	57%	63%	80%
74.5%	79%	81%	77%	83%	79%	86%	63%	63%	73%	83%	77%	59%	75%	74%	80%	80%	75%	62%	76%		64%
74.7%	78%	90%	76%	72%	79%	73%	78%	69%	72%	70%	85%	76%	76%	77%	68%	72%	63%	75%	78%	79%	62%
72.7%	62%	86%	76%	71%	67%	95%	74%	61%	69%	77%	80%	76%	69%	84%	66%	71%	59%	69%	77%	74%	64%
72.5%	72%	74%	77%	78%	75%	67%	72%	70%	70%	76%	71%	72%	73%	73%	75%	77%	71%	65%	73%	69%	72%
77.1%	79%	82%	83%	79%	63%	68%	74%	74%	78%	78%	83%	87%	85%	78%	78%	78%	81%	74%	81%	72%	65%
61.2%	70%	70%	70%	72%	64%	59%	68%	58%	60%	56%	62%	53%	54%	56%	61%	63%	56%	60%	61%	59%	54%
70.6%	79%	69%	79%	79%	77%	68%	79%	74%	65%	73%	72%	70%	64%	61%	76%	69%	67%	65%	63%	63%	70%
66.4%	72%	65%	70%	71%	68%	72%	57%	55%	63%	69%	73%	54%	67%	65%	76%	74%	58%	56%	73%	61%	76%
77.3%	74%	74%	71%	74%	85%	75%	80%	71%	85%	71%	71%	76%	74%	75%	78%	79%	83%	76%	83%	85%	84%
62.3%	68%	65%	68%	66%	55%	65%	59%	68%	55%	68%	68%	64%	65%	65%	61%	60%	57%	63%	57%	56%	56%
75.6%	87%	74%	76%	86%	83%	65%	83%	82%	88%	76%	77%	71%	70%	63%	80%	89%	73%	57%	60%	66%	81%
83.3%	88%	86%	91%	91%	50%	81%	92%	86%	92%	89%	90%	76%	81%	74%	89%	95%	93%	75%	69%	78%	83%
75.2%	76%	81%	81%	71%	66%	85%	74%	70%	69%	71%	74%	80%	85%	80%	58%	72%	79%	73%	84%		74%
77.2%	80%	76%	78%	75%	88%	84%	66%	56%	70%	82%	82%	64%	78%	77%	90%	78%	73%	75%	79%	80%	91%
77.4%	90%	76%	90%	90%	86%	84%	96%	84%	85%	84%	80%	64%	82%	70%	79%	78%	58%	63%	72%	60%	55%
79.7%	79%	87%	86%	88%	81%	90%	76%	67%	76%	86%	85%	74%	77%	85%	79%	76%	88%	64%	84%	77%	69%
94.5%	90%	93%	90%	92%	97%	93%	99%	90%	97%	90%	90%	95%	93%	93%	97%	98%	98%	95%	99%	97%	98%
79.6%	79%	79%	86%	85%	61%	71%	88%	87%	83%	87%	85%	78%	88%	77%	87%	80%	81%	81%	72%	49%	87%
86.4%	86%	84%	84%	91%	93%	84%	89%	84%	89%	92%	83%	98%	83%	85%	92%	83%	86%	80%	89%	81%	79%
91.5%	87%		90%	95%	90%	89%	95%	79%	94%	89%	92%	94%		95%	96%	93%	93%	82%	94%	99%	92%

Model Similarity Dendrogram

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