	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	1st 86.1%	3rd 84.6%	19th 76.8%	13th 79.7%	7th 82.7%	18th 77.0%	12th 80.3%	8th 82.7%	9th 81.9%	4th 84.0%	10th 81.2%	14th 79.2%	6th 83.4%	15th 79.2%	5th 83.9%	2nd 85.3%	16th 79.0%	21st 72.9%	11th 80.4%	20th 76.7%	17th 78.6%
85.2%	96%	92%	79%	89%	89%	65%	84%	92%	86%	85%	84%	76%	88%	79%	89%	89%	90%	78%	89%	85%	86%
87.0%	85%	76%	93%	94%	85%	87%	91%	85%	87%	92%	90%	91%	90%	90%	91%	90%	82%	83%	88%	83%	75%
65.0%	75%	69%	0%	74%	62%	77%	10%	73%	66%	77%	77%	74%	74%	75%	73%	68%	79%	66%	69%	55%	73%
92.2%	95%	85%	92%	92%	92%	89%	95%	94%	95%	93%	96%	92%	95%	87%	97%	96%	90%	89%	86%	91%	95%
89.4%	92%	91%	82%	88%	80%	99%	86%	94%	90%	99%	97%	92%	97%	91%	91%	97%	88%	65%	85%	97%	77%
88.7%	89%	95%	90%	90%	92%	93%	90%	89%	91%	86%	90%	91%	90%	82%	84%	86%	84%	89%	88%	82%	91%
87.4%	86%	82%	86%	87%	77%	93%	84%	88%	90%	89%	87%	91%	85%	95%	87%	90%	90%	86%	86%	90%	86%
78.8%	84%	79%	74%	76%	75%	50%	84%	91%	84%	77%	77%	76%	81%	67%	86%	92%	85%	85%	65%		88%
85.1%	87%	88%	80%	87%	84%	67%	76%	80%	83%	95%	88%	96%	89%	89%	91%	90%	92%	82%	76%	92%	76%
88.9%	92%	87%	92%	94%	92%	92%	85%	85%	92%	91%	84%	92%	91%	92%	87%	89%	77%	73%	92%	92%	96%
81.7%	87%	90%	92%	92%	88%	89%	90%	87%	86%	76%	85%	91%	74%	67%	77%	84%	66%	62%	86%	65%	81%
83.2%	92%	87%	90%	94%	86%	83%	85%	91%	87%	75%	75%	93%	70%	83%	90%	86%	78%	59%	91%	70%	82%
81.5%	79%	86%	84%	88%	88%	88%	81%	82%	82%	87%	91%	79%	87%	91%	73%	89%	70%	59%	88%	70%	70%
86.8%	86%	86%	87%	90%	81%	77%	90%	92%	88%	92%	94%	72%	90%	80%	93%	91%	87%	80%	92%	95%	80%
83.5%	84%	91%	87%	84%	89%	81%	91%	86%	88%	85%	89%	79%	89%	85%	82%	89%	74%	79%	82%	59%	81%
86.0%	97%	90%	97%	94%	94%	64%	82%	93%	86%	89%	74%	84%	89%	83%	94%	87%	87%	84%	84%	76%	77%
64.0%	72%	72%	72%	72%	66%	55%	68%	46%	71%	70%	65%	57%	57%	55%	69%	72%	70%	41%	62%	61%	71%
69.0%	80%	68%	78%	85%	72%	46%	59%	78%	66%	68%	54%	66%	72%	60%	71%	72%	77%	64%	69%	77%	68%
65.1%	70%	57%	74%	61%	58%	51%	67%	74%	68%	88%	61%	32%	77%	69%	84%	87%	63%	48%	55%	63%	61%
84.3%	97%	95%	95%	92%	96%	75%	95%	77%	77%	96%	81%	75%	93%	75%	88%	89%	75%	70%	75%	74%	80%
89.3%	93%	97%	87%	89%	94%	74%	94%	93%	91%	92%	94%	92%	94%	86%	95%	96%	82%	72%	79%		92%
86.4%	89%	90%	85%	85%	92%	76%	91%	90%	89%	89%	83%	91%	91%	90%	90%	96%	86%	67%	78%	83%	84%
78.3%	78%	71%	86%	80%	88%	88%	84%	84%	69%	87%	71%	81%	79%	88%	71%	75%	80%	63%	84%	73%	65%
85.9%	95%	94%	92%	97%	91%	93%	82%	85%	84%	94%	93%	74%	88%	85%	86%	92%	74%	74%	83%	74%	74%
86.7%	91%	90%	84%	91%	84%	88%	91%	84%	87%	91%	91%	75%	91%	80%	89%	91%	90%	90%	94%	69%	80%
77.9%	81%	82%	82%	84%	85%	78%	77%	78%	79%	85%	83%	80%	80%	79%	79%	83%	64%	62%	80%	74%	60%
75.0%	88%	79%	79%	83%	79%	62%	73%	86%	78%	75%	55%	75%	80%	62%	85%	81%	75%	60%	75%	71%	73%
78.0%	87%	89%	75%	73%	94%	59%	77%	88%	85%	80%	75%	66%	73%	62%	88%	81%	86%	82%	71%	83%	65%
74.6%	83%	91%	88%	90%	87%	64%	76%	67%	68%	70%	66%	80%	65%	62%	82%	82%	63%	62%	65%	80%	75%
76.5%	79%	82%	81%	87%	89%	72%	65%	79%	80%	75%	69%	62%	82%	73%	80%	80%	67%	89%	85%	65%	66%
84.1%	91%	84%	87%	88%	85%	82%	83%	84%	83%	84%	87%	82%	84%	86%	85%	87%	82%	77%	81%	82%	82%
77.4%	82%	89%	0%	0%	96%	80%	91%	84%	92%	80%	80%	83%	83%	82%	86%	89%	78%	80%	89%	97%	84%
59.5%	74%	64%	0%	0%	57%	72%	61%	68%	61%	71%	72%	69%	69%	69%	57%	63%	69%	72%	64%	50%	68%
79.6%	85%	80%	81%	90%	90%	75%	75%	77%	82%	82%	75%	72%	74%	74%	84%	85%	79%	80%	73%	80%	78%
71.4%	82%	85%	74%	80%	45%	73%	67%	65%	57%	60%	65%	82%	74%	68%	67%	71%	72%	81%	94%	75%	63%
84.8%	89%	87%	94%	91%	82%	82%	92%	91%	87%	88%	84%	80%	90%	80%	81%	83%	82%	74%	81%	79%	83%
87.0%	90%	83%	88%	85%	91%	90%	89%	80%	84%	84%	90%	87%	89%	87%	90%	90%	88%	84%	83%	88%	87%
88.3%	87%	93%	96%	92%	82%	92%	87%	92%	96%	93%	95%	81%	98%	85%	95%	90%	68%	67%	92%		85%
83.3%	95%	88%	89%	89%	85%	71%	86%	87%	84%	87%	83%	77%	89%	76%	90%	88%	81%	77%	66%	81%	81%
83.4%	96%	90%	0%	0%	83%	99%	87%	94%	86%	98%	99%	95%	95%	96%	87%	89%	100%	99%	90%	75%	94%
81.5%	87%	89%	81%	88%	95%	77%	87%	90%	89%	86%	82%	72%	81%	77%	87%	83%	74%	28%	89%	78%	91%
79.2%	85%	86%	76%	79%	81%	65%	83%	81%	81%	86%	79%	75%	81%	84%	81%	84%	76%	76%	79%	67%	79%
72.8%	69%	90%	74%	65%	57%	80%	64%	54%	68%	67%	80%	77%	77%	80%	76%	76%	76%	77%	76%	68%	77%

Model Similarity Dendrogram

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