	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 84.7%	5th 80.9%	3rd 82.6%	2nd 82.9%	9th 78.6%	21st 70.5%	10th 78.6%	6th 80.0%	11th 78.5%	7th 79.7%	12th 78.1%	16th 75.9%	13th 77.9%	19th 73.7%	8th 78.9%	4th 81.9%	14th 77.7%	18th 74.0%	15th 76.0%	17th 75.5%	20th 71.4%
81.8%		89%	83%	89%	78%	68%	82%	87%	82%	81%	81%	85%	84%	76%	82%	87%	85%	76%	80%	88%	74%
74.9%		65%	79%	87%	33%	86%	65%	77%	59%	80%	83%	88%	82%	79%	88%	84%	71%	69%	70%	78%	75%
63.9%		61%	66%	64%	66%	67%	64%	70%	58%	71%	68%	66%	66%	64%	56%	64%	62%	58%	63%	62%	62%
86.7%	88%	86%	90%	90%	90%	86%	88%	88%	87%	91%	87%	90%	85%	82%	87%	86%	80%	82%	82%	89%	86%
89.6%		90%	91%	93%	85%	82%	87%	93%	88%	96%	96%	94%	96%	96%	89%	90%	90%	85%	79%	81%	91%
85.4%		93%	95%	93%	93%	88%	90%	87%	88%	89%	93%	78%	85%	70%	87%	81%	82%	88%	89%		53%
78.5%	84%	77%	78%	78%	83%	72%	73%	81%	80%	80%	75%	81%	72%	80%	86%	84%	80%	84%	74%	80%	66%
73.8%		76%	71%	81%	81%	45%	71%	82%	82%	71%	67%	75%	66%	66%	91%	86%	75%	83%	64%	78%	66%
83.5%		87%	87%	82%	97%	67%	83%	89%	89%	93%	87%	72%	86%	84%	84%	88%	86%	90%	82%	69%	69%
90.0%	95%	90%	95%	94%	90%	98%	90%	79%	90%	94%	90%	93%	90%	90%	90%	90%	83%	75%	90%	90%	94%
84.5%		85%	84%	95%	91%	84%	87%	76%	90%	85%	91%	89%	80%	89%	87%	82%	87%	72%	81%	88%	67%
82.7%	90%	90%	93%	92%	93%	93%	81%	93%	89%	76%	73%	93%	59%	71%	88%	91%	62%	71%	92%	86%	60%
85.4%	77%	91%	92%	92%	85%	87%	87%	88%	87%	85%	86%	82%	88%	83%	89%	88%	81%	73%	84%	84%	84%
88.3%	91%	89%	91%	91%	87%	82%	93%	90%	93%	92%	92%	72%	96%	76%	86%	96%	93%	92%	93%	70%
82.4%	87%	81%	92%	91%	90%	67%	89%	90%	88%	78%	81%	89%	83%	75%	81%	81%	88%	69%	65%	83%	83%
74.3%		82%	88%	91%	80%	58%	79%	78%	72%	76%	71%	73%	80%	68%	75%	82%	82%	46%	79%	63%	63%
61.8%		68%	71%	69%	72%	52%	64%	44%	69%	60%	52%	61%	62%	52%	78%	71%	66%	46%	66%	53%	61%
67.9%		66%	84%	83%	71%	48%	60%	73%	63%	62%	60%	69%	71%	58%	70%	67%	72%	79%	71%	71%	60%
63.8%	73%	52%	70%	58%	75%	40%	56%	69%	64%	83%	56%	46%	79%	64%	84%	75%	66%	33%	44%	85%	68%
76.6%	79%	85%	77%	85%	78%	71%	83%	72%	72%	85%	74%	72%	72%	73%	82%	85%	73%	69%	72%	70%	80%
83.4%	89%	89%	89%	86%	86%	66%	88%	91%	87%	86%	85%	85%	90%	74%	91%	90%	85%	85%	72%	69%	69%
79.0%	79%	77%	76%	80%	83%	64%	82%	82%	84%	77%	75%	84%	78%	79%	85%	87%	84%	83%	69%	79%	73%
77.1%	80%	77%	85%	76%	92%	88%	88%	84%	69%	85%	87%	45%	82%	66%	73%	71%	73%	66%	76%	77%	79%
88.7%	88%	88%	92%	91%	87%	89%	88%	90%	90%	91%	89%	76%	87%	95%	92%	94%	87%	91%	83%	87%	87%
84.3%	82%	86%	85%	85%	85%	81%	88%	90%	89%	89%	88%	77%	87%	77%	85%	89%	85%	89%	94%	79%	61%
67.8%		73%	75%	70%	59%	64%	67%	67%	70%	63%	71%	67%	74%	71%	74%	70%	62%	75%	67%		49%
64.7%		67%	70%	78%	74%	45%	63%	69%	62%	65%	51%	64%	65%	61%	70%	72%	70%	65%	65%	64%	54%
73.4%	81%	88%	81%	80%	81%	48%	79%	83%	82%	73%	75%	62%	64%	56%	88%	82%	64%	83%	65%	72%	54%
71.0%	80%	87%	79%	81%	69%	64%	73%	68%	65%	64%	69%	72%	65%	60%	79%	78%	66%	69%	65%	63%	76%
77.1%		86%	91%	93%	81%	62%	63%	87%	77%	74%	74%	62%	73%	65%	79%	87%	86%	53%	85%	77%	87%
80.4%	85%	84%	87%	88%	88%	65%	84%	84%	86%	76%	82%	87%	81%	73%	85%	88%	81%	74%	76%	66%	69%
78.2%		86%	80%	82%	80%	80%	82%	76%	89%	75%	78%	80%	80%	82%	0%	82%	85%	89%	84%	89%	85%
56.4%		56%	62%	60%	62%	62%	60%	65%	54%	66%	64%	62%	62%	60%	0%	60%	58%	54%	59%	43%	58%
76.0%	81%	74%	80%	81%	79%	64%	71%	78%	77%	81%	73%	69%	75%	73%	81%	80%	80%	78%	71%	72%	78%
79.5%	88%	91%	91%	88%	51%	73%	73%	70%	65%	77%	72%	85%	79%	78%	88%	85%	85%	87%	88%		76%
83.3%	93%	92%	99%	93%	49%	82%	93%	90%	82%	92%	92%	79%	85%	74%	86%	89%	83%	69%	80%	83%	65%
78.3%		81%	81%	79%	84%	61%	82%	82%	79%	77%	80%	80%	75%	72%	84%	72%	87%	74%	76%	73%	87%
84.0%		86%	91%	86%	82%	86%	86%	84%	84%	94%	85%	79%	86%	84%	99%	91%	76%	79%	98%	82%	42%
74.0%	93%	77%	77%	78%	71%	54%	77%	91%	75%	78%	71%	73%	73%	60%	80%	77%	81%	70%	58%	74%	67%
95.1%		92%	98%	96%	98%	98%	96%	98%	89%	97%	100%	98%	98%	96%	87%	96%	93%	89%	95%	94%	94%
77.0%	84%	82%	66%	69%	79%	60%	79%	85%	91%	73%	80%	62%	74%	72%	77%	85%	77%	84%	82%	72%	85%
77.0%	81%	79%	77%	78%	76%	66%	80%	78%	79%	82%	73%	82%	78%	77%	84%	76%	69%	72%	71%	78%	82%
64.2%		78%	64%	67%	67%	67%	65%	42%	61%	64%	80%	65%	58%	67%	66%	62%	60%	65%	67%	60%	60%

Model Similarity Dendrogram

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