	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 76.0%	11th 74.9%	1st 76.9%	3rd 76.7%	9th 75.4%	15th 73.4%	8th 75.5%	5th 76.4%	2nd 76.9%	13th 73.9%	10th 75.3%	21st 70.4%	17th 72.9%	20th 71.0%	4th 76.4%	6th 76.1%	12th 74.2%	19th 72.7%	18th 72.7%	16th 73.1%	14th 73.9%
78.5%	77%	75%	91%	78%	86%	82%	77%	77%	89%	83%	77%	65%	82%	86%	74%	77%	70%	69%	75%	77%	82%
67.9%	62%	75%	58%	79%	31%	85%	70%	74%	62%	66%	79%	82%	70%	80%	75%	65%	62%	62%	77%	55%	56%
62.8%	75%	75%	74%	57%	57%	100%	57%	57%	57%	69%	57%	57%	57%	57%	57%	59%	68%	57%	57%	57%	57%
83.0%	91%	79%	92%	91%	89%	79%	89%	83%	86%	86%	74%	74%	85%	83%	85%	88%	78%	77%	78%	74%	81%
86.5%	91%	88%	91%	80%	88%	88%	81%	85%	85%	80%	88%	88%	88%	88%	86%	81%	88%	88%	88%	88%	88%
83.0%	83%	85%	73%	83%	83%	95%	84%	95%	83%	83%	83%	86%	86%	86%	82%	76%	77%	83%	80%	74%	83%
73.6%	76%	71%	71%	77%	63%	72%	68%	84%	78%	68%	63%	63%	68%	64%	84%	84%	85%	89%	63%	75%	80%
66.0%	58%	66%	63%	72%	65%	55%	63%	79%	58%	73%	65%	65%	61%	50%	73%	77%	78%	65%	73%	65%	61%
64.2%	64%	67%	67%	63%	74%	75%	70%	76%	82%	63%	59%	59%	63%	57%	56%	55%	50%	62%	64%	66%	56%
73.1%	74%	74%	74%	78%	74%	74%	66%	53%	71%	70%	78%	74%	78%	74%	80%	78%	69%	71%	74%	73%	78%
61.5%	65%	70%	85%	73%	63%	70%	70%	65%	58%	55%	67%	54%	57%	37%	60%	50%	45%	40%	61%	65%	82%
84.6%	79%	86%	86%	82%	94%	77%	90%	86%	87%	85%	89%	78%	80%	87%	85%	87%	85%	92%	82%	87%	73%
79.9%	79%	79%	75%	79%	80%	71%	77%	80%	91%	77%	82%	82%	77%	82%	82%	77%	78%	83%	82%	82%	82%
67.8%	73%	67%	65%	67%	71%	76%	64%	69%	62%	73%	70%	63%	70%	68%	69%	63%	63%	70%	66%	67%	68%
80.4%	79%	79%	79%	79%	82%	82%	80%	82%	90%	76%	86%	80%	80%	79%	77%	81%	86%	84%	86%	77%	64%
77.9%	81%	80%	81%	83%	82%	78%	78%	80%	77%	80%	78%	67%	78%	80%	82%	82%	80%	55%	76%	75%	83%
79.5%	82%	78%	86%	83%	80%	80%	82%	78%	76%	81%	83%	78%	74%	83%	80%	77%	70%	78%	91%	74%	75%
71.7%	74%	67%	77%	71%	82%	78%	66%	78%	67%	69%	63%	52%	67%	72%	76%	75%	85%	72%	75%	67%	72%
60.3%	67%	55%	67%	55%	73%	64%	63%	51%	63%	61%	49%	46%	63%	60%	76%	67%	55%	62%	46%	71%	53%
72.2%	73%	72%	76%	78%	78%	73%	72%	72%	75%	71%	59%	70%	72%	72%	70%	78%	74%	74%	76%	73%	59%
85.1%	93%	77%	84%	84%	94%	94%	80%	92%	84%	83%	85%	76%	94%	85%	85%	94%	89%	76%	77%	77%	85%
77.0%	87%	78%	87%	81%	82%	74%	78%	75%	78%	74%	75%	76%	76%	76%	79%	78%	67%	67%	79%	76%	75%
74.6%	65%	70%	74%	68%	95%	83%	82%	84%	85%	82%	86%	51%	75%	89%	62%	68%	60%	59%	85%		68%
85.3%	91%	90%	100%	91%	81%	78%	80%	79%	82%	83%	82%	82%	82%	82%	91%	100%	86%	82%	100%	82%	67%
71.3%	71%	75%	65%	72%	65%	67%	72%	77%	75%	67%	75%	65%	73%	74%	75%	70%	76%	74%	75%	75%	59%
72.8%	73%	80%	79%	85%	77%	54%	80%	67%	76%	69%	82%	85%	64%	67%	68%	82%	60%	67%	68%	79%	66%
70.5%	74%	58%	79%	77%	68%	63%	76%		70%	76%	58%	63%	66%	74%	73%	76%	75%	61%	70%	70%	83%
79.7%	79%	82%	80%	80%	73%	66%	81%	85%	85%	75%	82%	69%	87%	65%	85%	85%	87%	88%	75%	83%	81%
60.7%	64%	72%	75%	76%	60%	56%	61%	55%	62%	55%	51%	51%	56%	57%	62%	64%	57%	57%	63%	58%	63%
62.1%	74%	69%	63%	72%	65%	55%	58%	66%	63%	59%	72%	59%	59%	59%	69%	71%	66%	59%	68%	10%	69%
78.8%	80%	80%	75%	75%	78%	73%	78%	69%	78%	83%	78%	76%	77%	70%	87%	83%	84%	80%	80%	83%	87%
76.5%	57%	57%	57%	81%	100%	57%	100%	100%	100%	74%	100%	100%	57%	57%	74%	74%	74%	57%	57%	100%	74%
64.3%	75%	75%	74%	57%	57%	100%	57%	57%	57%	69%	57%	57%	57%	57%	68%	69%	68%	57%	57%	57%	69%
78.0%	86%	75%	77%	81%	84%	66%	70%	90%	90%	78%	63%	61%	85%	72%	81%	81%	77%	89%	73%	75%	83%
75.2%	77%	85%	87%	85%	43%	72%	76%	78%	82%	68%	69%	75%	65%	65%	85%	76%	83%	77%	69%	76%	87%
79.8%	91%	88%	91%	66%	63%	69%	92%	84%	85%	81%	85%	65%	92%	71%	75%	84%	76%	71%	78%		90%
68.0%	69%	69%	65%	69%	65%	72%	73%	62%	64%	60%	67%	78%	64%	61%	71%	69%	72%	72%	69%	69%	69%
91.3%	92%	94%	92%	88%	84%	95%	88%	87%	92%	93%	93%	90%	92%	88%	100%	95%	100%	92%	88%	92%	83%
76.2%	76%	80%	76%	76%	80%	63%	76%	86%	76%	88%	80%	78%	85%	71%	78%	71%	72%	73%	71%	71%	74%
78.6%	57%	57%	57%	81%	100%	57%	100%	100%	100%	74%	100%	100%	57%	57%	74%	74%	74%	100%	57%	100%	74%
68.8%	73%	60%	80%	84%	84%	47%	66%	60%	73%	69%	91%	51%	67%	53%	77%	70%	77%	73%	50%	66%	73%
71.4%	79%	81%	66%	75%	70%	53%	74%	70%	66%	65%	76%	57%	65%	78%	80%	77%	81%	66%	67%	72%	81%
84.0%	81%	81%	92%	86%	81%	90%	82%	80%	85%	85%	81%	81%	85%	82%	76%	86%	84%	94%	81%	85%	85%

Model Similarity Dendrogram

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