	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	- -	12th 81.7%	3rd 84.2%	1st 85.0%	11th 82.3%	20th 78.0%	10th 82.4%	9th 82.5%	6th 83.6%	5th 83.7%	13th 81.5%	18th 80.4%	7th 83.4%	19th 79.1%	2nd 84.5%	4th 84.0%	14th 81.3%	17th 80.5%	15th 81.2%	16th 81.0%	8th 83.0%
81.4%		79%	84%	85%	80%	81%	83%	81%	86%	82%	84%	84%	81%	82%	84%	81%	77%	73%	82%	79%	79%
86.8%		90%	85%	94%	84%	87%	94%	77%	85%	89%	95%	80%	92%	80%	91%	84%	93%	77%	89%	90%	81%
70.5%		73%	61%	70%	72%	52%	96%	62%	60%	73%	72%	86%	72%	72%	73%	73%	73%	72%	52%	73%	73%
86.4%		83%	89%	92%	81%	86%	89%	86%	88%	86%	89%	95%	88%	67%	87%	84%	92%	92%	78%	95%	81%
95.9%		96%	96%	97%	96%	96%	98%	94%	99%	94%	96%	96%	96%	96%	96%	95%	99%	96%	96%	96%	89%
91.2%		97%	92%	97%	100%	88%	92%	90%	90%	91%	89%	95%	89%	86%	96%	94%	80%	86%	96%	86%	90%
89.5%		88%	93%	97%	84%	83%	90%	97%	90%	94%	86%	88%	88%	84%	98%	93%	92%	93%	83%		80%
74.7%		75%	75%	79%	74%	66%	71%	74%	73%	80%	69%	74%	73%	68%	76%	80%	76%	76%	75%	74%	86%
83.6%		78%	79%	76%	83%	75%	89%	91%	86%	85%	83%	95%	90%	86%	76%	88%	79%	78%	83%	90%	82%
89.0%		95%	93%	92%	95%	95%	84%	88%	97%	86%	79%	89%	95%	95%	87%	82%	76%	75%	95%	92%	90%
75.1%		84%	85%	85%	72%	82%	77%	85%	73%	69%	78%	84%	70%	66%	70%	71%	62%	52%	76%	86%	75%
76.8%		81%	81%	81%	83%	72%	73%	85%	83%	75%	66%	76%	77%	76%	82%	71%	75%	71%	79%	73%
86.3%		85%	91%	88%	86%	80%	88%	92%	87%	84%	86%	87%	86%	86%	88%	84%	85%	84%	86%	87%	86%
89.7%		89%	83%	91%	88%	91%	86%	89%	88%	94%	92%	83%	92%	98%	89%	88%	94%	83%	93%	91%	92%
89.8%		93%	89%	88%	95%	90%	90%	93%	94%	90%	90%	91%	91%	89%	83%	87%	79%	89%	92%		94%
89.7%		82%	90%	91%	96%	85%	92%	95%	94%	88%	85%	71%	91%	91%	87%	91%	93%	92%	95%	92%	93%
70.9%		78%	82%	76%	66%	65%	68%	47%	70%	78%	76%	73%	56%	66%	79%	78%	81%	58%	69%		81%
73.0%		65%	73%	74%	72%	69%	73%	78%	77%	71%	71%	54%	74%	77%	75%	80%	72%	90%	69%	66%	79%
62.5%		46%	64%	56%	67%	46%	68%	60%	69%	74%	60%	38%	71%	60%	76%	80%	49%	72%	51%	79%	65%
86.9%		77%	93%	93%	93%	91%	95%	95%	95%	97%	70%	73%	92%	95%	81%	80%	87%	85%	97%	73%	76%
83.4%		79%	82%	85%	87%	87%	82%	85%	80%	92%	82%	83%	90%	80%	91%	89%	82%	83%	77%	75%	76%
89.6%		88%	88%	88%	85%	93%	88%	91%	91%	91%	85%	87%	92%	84%	88%	94%	90%	89%	94%	90%	96%
77.9%		79%	79%	78%	81%	77%	86%	82%	74%	86%	87%	67%	68%	77%	76%	78%	79%	79%	79%	71%	75%
81.7%		78%	83%	92%	86%	89%	87%	83%	86%	90%	86%	86%	88%	86%	80%	83%	82%	80%	82%	10%	96%
87.2%		85%	82%	86%	90%	93%	81%	89%	92%	90%	86%	79%	86%	82%	89%	88%	86%	91%	89%	92%	87%
79.1%		88%	85%	84%	72%	71%	79%	70%	79%	80%	88%	86%	78%	72%	85%	84%	68%	70%	86%	78%	80%
80.3%		66%	88%	82%	79%	80%	81%	88%	78%	78%	63%	72%	84%	77%	88%	75%	90%	77%	83%	84%	92%
84.5%		85%	86%	85%	92%	80%	89%	87%	93%	90%	81%	68%	86%	63%	92%	88%	87%	95%	79%	77%	87%
74.6%		91%	85%	87%	82%	72%	79%	70%	72%	69%	73%	67%	69%	68%	77%	75%	70%	67%	75%	71%	73%
81.6%		83%	86%	89%	87%	72%	78%	85%	84%	78%	77%	80%	84%	80%	82%	80%	87%	79%	77%	85%	79%
88.6%		89%	92%	91%	87%	89%	87%	92%	91%	87%	86%	87%	90%	87%	90%	89%	88%	83%	90%	87%	89%
67.3%		61%	66%	60%	79%	51%	61%	76%	79%	61%	79%	79%	61%	52%	61%	61%	61%	79%	79%	79%	61%
67.1%		69%	59%	66%	68%	49%	96%	59%	60%	69%	68%	82%	68%	68%	69%	69%	69%	69%	49%	68%	69%
79.0%		73%	85%	86%	85%	74%	76%	82%	80%	79%	77%	73%	80%	66%	86%	90%	75%	83%	73%	77%	79%
77.8%		84%	91%	86%	53%	69%	73%	69%	74%	70%	77%	79%	80%	81%	84%	84%	83%	75%	87%	73%	83%
87.1%		90%	86%	86%	86%	79%	94%	94%	90%	93%	86%	86%	93%	69%	89%	88%	87%	84%	79%	94%	90%
85.9%		94%	93%	93%	90%	91%	10%	86%	93%	92%	88%	87%	92%	84%	94%	93%	90%	85%	83%	91%	90%
92.0%		91%	91%	91%	82%	93%	93%	89%	90%	92%	89%	96%	97%	96%	95%	95%	92%	87%	96%	96%	90%
86.3%		88%	91%	92%	87%	81%	88%	90%	83%	92%	86%	82%	92%	79%	90%	89%	85%	90%	79%	81%	81%
84.6%		68%	98%	92%	79%	82%	90%	84%	83%	90%	79%	85%	90%	79%	90%	90%	87%	79%	79%	79%	90%
79.0%		75%	78%	89%	71%	62%	81%	83%	88%	79%	90%	66%	86%	68%	82%	89%	74%	80%	66%	90%	82%
86.4%		93%	87%	87%	79%	65%	87%	86%	85%	85%	91%	85%	83%	91%	92%	90%	91%	88%	89%	85%	88%
82.4%		84%	83%	80%	84%	75%	82%	67%	84%	84%	83%	83%	86%	93%	88%	87%	80%	74%	86%	83%	83%

Model Similarity Dendrogram

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