	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 78.5%	7th 77.0%	1st 80.0%	2nd 79.8%	15th 73.5%	20th 71.2%	10th 74.6%	11th 74.5%	12th 74.4%	6th 77.3%	9th 76.3%	18th 72.6%	5th 77.4%	17th 73.3%	3rd 78.5%	8th 76.9%	16th 73.4%	19th 72.1%	13th 74.2%	21st 70.8%	14th 73.8%
74.2%	72%	68%	82%	76%	74%	67%	84%	76%	78%	75%	78%	77%	78%	75%	74%	67%	70%	55%	77%	74%	82%
71.1%	68%	71%	72%	69%	77%	69%	71%	65%	70%	72%	71%	71%	74%	76%	72%	75%	69%	65%	75%	73%	68%
70.1%	70%	64%	78%	77%	58%	70%	68%	66%	58%	75%	78%	74%	77%	74%	68%	64%	74%	74%	60%	71%	75%
89.4%	86%	90%	89%	94%	83%	90%	89%	78%	86%	93%	94%	95%	93%	88%	86%	89%	93%	86%	92%		94%
88.4%	87%	89%	91%	89%	90%	88%	93%	92%	88%	87%	91%	94%	96%	85%	90%	84%	87%	90%	85%	88%	72%
84.6%	95%	92%	93%	93%	88%	84%	84%	77%	75%	87%	83%	88%	78%	80%	89%	87%	88%	70%	84%	74%	87%
83.0%	84%	80%	84%	85%	74%	83%	80%	84%	89%	82%	84%	79%	80%	82%	89%	89%	82%	86%	78%	82%	86%
79.4%	80%	82%	82%	83%	74%	56%	72%	87%	87%	75%	77%	80%	83%	68%	87%	88%	85%	91%	67%	80%	84%
79.9%	87%	91%	91%	91%	69%	64%	75%	77%	75%	85%	88%	83%	88%	88%	85%	84%	83%	74%	84%	58%	58%
92.3%	95%	81%	96%	97%	95%	95%	90%	83%	95%	95%	95%	81%	95%	95%	96%	92%	84%	89%	95%	95%	100%
79.0%	87%	81%	92%	87%	70%	98%	92%	92%	87%	67%	73%	88%	75%	68%	74%	72%	90%	65%	90%	59%	52%
80.4%	96%	76%	81%	86%	86%	84%	84%	85%	85%	73%	80%	86%	70%	58%	83%	78%	79%	69%	85%	82%	83%
72.4%	67%	74%	73%	77%	75%	80%	70%	76%	70%	75%	76%	67%	71%	75%	75%	69%	74%	55%	76%	72%	74%
70.9%	75%	74%	76%	76%	77%	61%	74%	74%	77%	70%	73%	63%	75%	51%	73%	71%	70%	60%	71%	68%	80%
71.5%	75%	74%	73%	76%	70%	72%	71%	58%	64%	75%	71%	55%	75%	71%	73%	79%	70%	78%	72%	71%	79%
77.7%	80%	82%	82%	80%	80%	62%	79%	81%	76%	82%	79%	75%	80%	71%	79%	84%	77%	74%	78%	71%	79%
58.7%	63%	65%	66%	64%	51%	46%	60%	46%	57%	57%	60%	60%	59%	51%	69%	66%	57%	56%	60%	56%	63%
69.7%	74%	74%	76%	82%	68%	45%	61%	70%	65%	72%	58%	65%	75%	58%	76%	71%	83%	74%	67%	79%	71%
58.5%	60%	39%	52%	47%	89%	37%	54%	66%	62%	68%	45%	35%	65%	65%	83%	87%	63%	73%	36%	67%	36%
68.5%	75%	78%	76%	75%	72%	60%	73%	68%	67%	76%	61%	60%	73%	63%	77%	70%	60%	54%	69%	64%	67%
77.5%	78%	83%	92%	84%	80%	73%	84%	84%	81%	84%	80%	78%	83%	78%	69%	77%	62%	75%	66%	81%	56%
71.4%	67%	72%	73%	71%	63%	74%	68%	68%	67%	80%	77%	70%	73%	75%	80%	59%	73%	62%	74%	77%	77%
76.3%	79%	76%	70%	81%	81%	82%	75%	77%	75%	84%	78%	76%	78%	75%	72%	74%	72%	76%	79%	77%	66%
80.2%	83%	87%	85%	85%	82%	76%	85%	79%	86%	86%	83%	67%	83%	81%	80%	86%	73%	68%	74%	73%	83%
68.8%	69%	70%	80%	74%	65%	66%	79%	68%	79%	73%	81%	53%	77%	68%	77%	69%	52%	47%	73%	80%	45%
65.7%	64%	71%	66%	63%	77%	69%	62%	68%	69%	74%	66%	62%	72%	76%	63%	73%	52%	50%	72%	64%	46%
71.8%	76%	78%	82%	81%	73%	50%	72%	77%	72%	78%	60%	73%	77%	63%	78%	74%	74%	70%	70%	56%	73%
81.1%	92%	86%	82%	82%	91%	65%	82%	86%	89%	86%	74%	78%	81%	65%	91%	90%	87%	74%	73%	68%	81%
75.4%	78%	85%	86%	85%	76%	62%	79%	73%	78%	68%	77%	76%	68%	64%	83%	74%	68%		78%	76%	73%
72.6%	78%	76%	76%	82%	78%	52%	57%	78%	68%	78%	81%	57%	81%	69%	77%	77%	67%	90%	68%	66%	69%
56.7%	63%	53%	62%	60%	57%	62%	46%	46%	51%	60%	61%	43%	56%	59%	67%	67%	52%	50%	55%	56%	65%
64.2%	60%	70%	56%	66%	77%	64%	73%	69%	77%	59%	56%	60%	57%	60%	71%	70%	60%	64%	74%	37%	69%
78.5%	83%	73%	88%	83%	66%	79%	70%	75%	66%	85%	88%	83%	86%	83%	72%	73%	83%	79%	69%		85%
69.4%	77%	66%	72%	74%	80%	66%	60%	80%	67%	77%	65%	65%	69%	65%	80%	71%	67%	71%	60%	60%	66%
80.4%	89%	88%	85%	86%	47%	81%	77%	77%	83%	78%	77%	84%	84%	75%	89%	75%	84%	90%	77%	79%	84%
73.5%	71%	80%	77%	77%	52%	87%	72%	73%	65%	68%	70%	83%	74%	81%	65%	67%	72%	74%	82%	77%	77%
76.9%	86%	79%	84%	87%	73%	76%	66%	66%	70%	80%	83%	61%	74%	76%	85%	86%	70%	74%	80%	73%	86%
86.5%	83%	91%	95%	95%	80%	91%	89%	91%	88%	92%	85%	72%	95%	85%	91%	87%	64%	93%	85%	85%	80%
73.6%	80%	77%	82%	81%	74%	80%	74%	68%	71%	76%	76%	70%	75%	68%	75%	71%	67%	67%	70%	74%	70%
88.7%	97%	84%	99%	94%	77%	90%	81%	86%	77%	96%	99%	94%	97%	94%	77%	84%	94%	90%	80%	77%	96%
83.5%	95%	91%	90%	91%	49%	86%	91%	92%	82%	82%	90%	83%	87%	92%	85%	88%	83%	85%	89%	42%	80%
75.2%	77%	78%	76%	75%	80%	51%	76%	68%	68%	70%	82%	78%	73%	83%	79%	78%	78%	80%	76%	76%	77%
68.8%	73%	71%	75%	70%	63%	67%	65%	54%	58%	68%	76%	81%	70%	74%	70%	72%	64%	60%	67%	65%	81%

Model Similarity Dendrogram

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