	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	7th 78.0%	12th 76.6%	2nd 80.2%	3rd 80.1%	11th 76.9%	21st 70.7%	14th 75.6%	10th 77.4%	5th 78.4%	9th 77.5%	13th 76.4%	19th 73.1%	7th 78.0%	18th 73.2%	1st 80.6%	4th 79.2%	15th 75.4%	20th 72.9%	16th 74.6%	17th 73.6%	6th 78.0%
85.1%	85%	84%	89%	89%	95%	85%	88%	81%	94%	91%	91%	88%	88%	78%	89%	88%	77%	67%	80%	84%	76%
72.1%	70%	77%	76%	76%	58%	80%	76%	75%	69%	72%	74%	75%	75%	83%	72%	75%	62%	55%	78%	76%	61%
77.9%	82%	82%	82%	88%	82%	49%	74%	72%	82%	82%	82%	82%	82%	74%	82%	82%	82%	82%	49%	82%	82%
78.0%	80%	85%	85%	85%	84%	73%	77%	83%	83%	77%	80%	70%	70%	65%	82%	83%	79%	71%	78%	70%	77%
81.2%	78%	78%	82%	84%	78%	78%	87%	83%	84%	81%	78%	78%	80%	78%	91%	88%	86%	78%	78%	78%	79%
82.9%	76%	80%	70%	77%	80%	86%	95%	80%	86%	84%	85%	81%	90%	91%	79%	82%	84%	89%	80%	84%	82%
74.1%	83%	70%	78%	81%	74%	66%	70%	73%	80%	68%	63%	57%	73%	63%	87%	85%	81%	80%	63%	75%	86%
70.5%	72%	73%	77%	72%	80%	54%	65%	77%	66%	70%	80%	64%	69%	62%	76%	75%	78%	70%	64%	70%	66%
71.6%	60%	50%	71%	71%	83%	86%	82%	80%	88%	75%	89%	61%	70%	61%	72%	64%	55%	66%	75%	75%	70%
70.8%	70%	70%	80%	72%	70%	70%	62%	53%	70%	71%	82%	70%	70%	70%	79%	75%	74%	63%	70%	70%	76%
76.7%	85%	93%	91%	89%	86%	66%	91%	93%	73%	67%	80%	73%	74%	66%	83%	75%	57%	50%	65%	91%	63%
76.6%	81%	85%	86%	86%	82%	82%	78%	77%	75%	71%	77%	82%	74%	72%	82%	75%	66%	60%	82%	54%	82%
80.3%	79%	86%	75%	83%	78%	70%	79%	79%	86%	84%	80%	85%	86%	80%	80%	82%	76%	78%	80%	80%	80%
81.9%	82%	86%	90%	88%	77%	75%	84%	91%	85%	86%	77%	63%	86%	72%	91%	90%	78%	77%	77%	91%	73%
83.8%	89%	85%	84%	84%	80%	80%	83%	86%	97%	84%	81%	86%	81%	81%	76%	83%	86%	78%	82%		89%
81.9%	77%	85%	83%	88%	82%	81%	84%	88%	75%	88%	90%	71%	82%	75%	90%	91%	76%	71%	80%	74%	89%
85.7%	86%	88%	96%	85%	74%	84%	86%	69%	87%	95%	87%	82%	81%	80%	95%	87%	84%	81%	89%	88%	96%
81.8%	86%	79%	81%	81%	81%	84%	66%	77%	87%	69%	83%	78%	81%	92%	83%	81%	95%	94%	76%	77%	87%
64.4%	71%	51%	59%	58%	83%	49%	58%	60%	64%	74%	63%	48%	67%	58%	81%	76%	69%	66%	53%	79%	66%
78.5%	94%	53%	90%	86%	80%	72%	88%	87%	80%	86%	53%	71%	92%	71%	76%	81%	91%	76%	88%	71%	62%
78.0%	84%	71%	83%	83%	80%	70%	72%	81%	74%	84%	75%	83%	81%	73%	84%	81%	79%	73%	72%	74%	81%
83.5%	85%	89%	84%	79%	79%	85%	86%	87%	80%	93%	86%	83%	83%	86%	90%	84%	71%	77%	81%	75%	90%
84.2%	82%	83%	83%	82%	85%	77%	97%	86%	92%	90%	88%	67%	93%	81%	85%	81%	79%	85%	86%	77%	90%
79.4%	84%	63%	90%	92%	80%	75%	78%	78%	74%	87%	80%	71%	80%	80%	80%	78%	83%	76%	80%	80%	78%
69.5%	72%	72%	72%	72%	77%	64%	72%	75%	72%	75%	70%	64%	75%	76%	72%	75%	71%	78%	77%	10%	68%
68.5%	62%	76%	75%	76%	72%	55%	72%	68%	72%	76%	73%	66%	66%	54%	74%	80%	59%	54%	76%		63%
70.7%	74%	65%	77%	74%	83%	78%	66%	72%	74%	60%	49%	75%	69%	75%	81%	62%	67%	59%	72%	74%	78%
80.4%	87%	85%	86%	86%	85%	53%	73%	94%	92%	86%	90%	70%	86%	64%	92%	83%	81%	76%	65%	72%	82%
71.7%	71%	87%	80%	85%	80%	66%	70%	67%	69%	70%	67%	67%	67%	67%	75%	75%	70%	67%	67%	67%	72%
76.0%	79%	80%	72%	78%	80%	63%	76%	79%	71%	70%	80%	79%	79%	79%	74%	72%	82%	82%	80%	76%	66%
79.1%	77%	76%	78%	79%	83%	68%	79%	79%	80%	83%	78%	78%	78%	78%	83%	83%	74%	81%	84%		83%
54.9%	49%	49%	58%	58%	66%	66%	28%	71%	57%	49%	49%	66%	49%	28%	49%	49%	49%	66%	49%	66%	82%
57.6%	53%	53%	65%	63%	74%	58%	53%	51%	58%	53%	58%	58%	58%	74%	53%	53%	53%	58%	58%	53%	53%
76.9%	81%	68%	81%	88%	88%	71%	65%	77%	78%	72%	75%	71%	79%	71%	83%	86%	81%	81%	64%	74%	81%
71.1%	77%	77%	81%	89%	32%	62%	70%	59%	58%	54%	63%	77%	76%	76%	76%	85%	81%	60%	84%	64%	92%
77.1%	82%	81%	76%	76%	55%	71%	90%	81%	86%	78%	67%	78%	86%	78%	76%	76%	73%	77%	78%	81%	74%
80.0%	84%	87%	82%	78%	78%	75%	81%	82%	83%	80%	78%	77%	81%	84%	78%	80%	77%	71%	86%	78%	81%
85.1%	90%	91%	88%	85%	81%	88%	88%	89%	93%	88%	91%	78%	83%	78%	90%	86%	72%	83%	78%		82%
80.1%	82%	85%	83%	83%	79%	67%	77%	83%	80%	85%	79%	76%	83%	78%	80%	80%	80%	82%	77%	83%	81%
81.5%	72%	82%	92%	71%	66%	66%	58%	93%	97%	94%	82%	97%	94%	58%	94%	94%	94%	66%	82%	66%	94%
77.2%	84%	77%	76%	83%	79%	62%	77%	78%	79%	79%	77%	65%	78%	69%	81%	83%	80%	80%	77%	77%	80%
77.2%	82%	79%	80%	82%	77%	56%	78%	78%	76%	79%	81%	59%	83%	83%	81%	80%	80%	72%	72%	76%	87%
74.5%	73%	77%	82%	78%	61%	72%	71%	58%	67%	73%	74%	74%	74%	87%	88%	80%	70%	77%	77%	77%	74%

Model Similarity Dendrogram

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