	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 86.3%	3rd 85.6%	18th 78.5%	20th 78.4%	8th 83.2%	19th 78.4%	11th 82.7%	7th 83.2%	9th 83.0%	5th 84.4%	10th 82.8%	16th 80.1%	6th 84.0%	15th 80.1%	4th 85.0%	2nd 85.6%	17th 79.4%	21st 77.1%	12th 81.4%	14th 80.4%	13th 81.2%
88.5%	97%	94%	81%	91%	91%	71%	86%	95%	91%	87%	87%	87%	93%	80%	94%	95%	95%	78%	88%	90%	88%
85.0%	82%	78%	92%	90%	77%	91%	89%	81%	85%	88%	89%	81%	89%	90%	92%	91%	75%	76%	81%	82%	87%
63.6%	72%	67%	0%	0%	60%	70%	64%	71%	60%	74%	72%	79%	78%	70%	64%	65%	75%	64%	63%	97%	70%
92.0%	94%	84%	96%	91%	96%	87%	92%	93%	96%	94%	93%	92%	95%	95%	97%	92%	87%	87%	92%	91%	88%
90.1%	89%	90%	87%	87%	89%	89%	90%	89%	91%	96%	99%	95%	95%	98%	92%	94%	89%	88%	81%	87%	78%
86.1%	93%	95%	89%	90%	91%	91%	87%	87%	88%	88%	88%	75%	82%	77%	83%	83%	86%	89%	90%	66%	90%
88.6%	89%	85%	87%	86%	84%	88%	86%	94%	91%	87%	88%	91%	87%	91%	93%	90%	90%	91%	80%	89%	93%
81.4%	89%	81%	78%	78%	76%	56%	84%	95%	83%	80%	77%	80%	87%	78%	90%	89%	92%	80%	69%	77%	91%
85.2%	86%	82%	81%	84%	83%	70%	78%	81%	83%	93%	87%	92%	90%	91%	86%	91%	89%	96%	80%	89%	77%
91.0%	96%	92%	94%	94%	92%	96%	90%	82%	92%	89%	92%	95%	85%	92%	89%	92%	79%	89%	92%	92%	96%
82.1%	85%	90%	92%	91%	81%	90%	77%	87%	85%	66%	89%	92%	71%	68%	79%	80%	69%	74%	85%	85%	89%
87.2%	95%	88%	88%	96%	93%	89%	79%	92%	91%	77%	77%	95%	71%	86%	88%	83%	89%	90%	95%	80%	90%
80.9%	80%	93%	91%	91%	87%	89%	80%	77%	77%	88%	88%	79%	82%	92%	75%	87%	71%	44%	87%	70%	70%
89.0%	92%	87%	91%	92%	91%	84%	91%	93%	93%	96%	92%	72%	95%	72%	90%	96%	81%	85%	94%	94%	87%
86.8%	92%	90%	94%	89%	81%	82%	92%	88%	87%	88%	90%	82%	89%	90%	89%	90%	86%	77%	81%	82%	83%
86.4%	96%	93%	95%	90%	87%	77%	83%	90%	86%	87%	81%	82%	91%	77%	91%	91%	87%	79%	86%	82%	84%
68.2%	75%	92%	74%	75%	71%	59%	71%	50%	67%	70%	62%	58%	60%	59%	78%	77%	66%	62%	68%	65%	73%
72.7%	83%	72%	81%	80%	68%	52%	61%	85%	72%	74%	60%	74%	74%	58%	77%	76%	78%	70%	76%	85%	70%
64.5%	65%	56%	68%	62%	75%	40%	67%	75%	73%	83%	60%	50%	75%	63%	78%	81%	60%	51%	56%	69%	48%
87.0%	95%	94%	96%	92%	91%	78%	94%	80%	78%	98%	82%	79%	97%	79%	92%	96%	80%	81%	79%	79%	87%
87.9%	86%	94%	90%	90%	94%	75%	94%	89%	92%	91%	95%	92%	95%	86%	83%	85%	80%	82%	80%	89%	83%
85.8%	82%	89%	87%	86%	86%	77%	90%	88%	87%	90%	83%	88%	92%	90%	91%	91%	70%	83%	78%	84%	90%
81.8%	82%	72%	82%	82%	95%	91%	89%	90%	77%	89%	89%	67%	84%	80%	73%	78%	78%	74%	88%	87%	71%
86.2%	91%	92%	96%	90%	89%	90%	84%	86%	84%	96%	96%	75%	89%	86%	85%	96%	76%	77%	81%	76%	76%
88.3%	89%	95%	92%	92%	93%	85%	93%	91%	95%	94%	94%	70%	91%	72%	93%	79%	94%	93%	92%	81%	77%
77.6%	80%	78%	79%	80%	85%	77%	75%	72%	80%	79%	82%	79%	77%	84%	80%	87%	64%	66%	80%	68%	77%
75.7%	87%	79%	78%	82%	73%	64%	74%	81%	76%	75%	57%	75%	79%	63%	86%	79%	77%	71%	77%	77%	79%
85.2%	92%	96%	90%	89%	94%	63%	84%	94%	91%	88%	84%	75%	86%	67%	95%	92%	81%	83%	76%	84%	85%
78.3%	88%	93%	88%	93%	81%	71%	79%	73%	81%	72%	72%	81%	70%	69%	83%	85%	69%	77%	72%	71%	77%
76.0%	81%	85%	85%	88%	86%	80%	66%	82%	81%	77%	75%	66%	73%	71%	84%	78%	67%	44%	76%	83%	68%
83.4%	85%	81%	81%	90%	87%	82%	83%	84%	82%	84%	89%	86%	84%	87%	81%	88%	78%	74%	83%	80%	83%
72.5%	78%	84%	0%	0%	91%	80%	80%	79%	91%	76%	78%	71%	72%	80%	81%	85%	75%	74%	87%	80%	80%
60.6%	69%	64%	0%	0%	57%	67%	67%	68%	57%	71%	69%	76%	75%	67%	62%	71%	72%	73%	60%		67%
83.1%	91%	84%	84%	91%	91%	79%	81%	83%	82%	84%	79%	78%	83%	78%	84%	84%	84%	87%	77%	80%	82%
73.3%	80%	90%	84%	79%	47%	60%	66%	65%	67%	65%	64%	70%	73%	75%	79%	77%	72%	69%	95%	91%	72%
83.4%	83%	88%	90%	84%	69%	85%	91%	90%	82%	85%	82%	83%	90%	84%	79%	83%	87%	71%	84%	84%	78%
86.1%	87%	87%	84%	83%	91%	90%	87%	77%	86%	84%	89%	90%	89%	93%	83%	81%	84%	81%	84%	87%	92%
85.8%	88%	91%	95%	93%	87%	94%	90%	91%	94%	94%	91%	75%	94%	75%	93%	94%	75%	62%	94%	49%	83%
86.0%	91%	87%	94%	94%	92%	76%	91%	88%	86%	93%	83%	83%	90%	81%	93%	88%	83%	75%	72%	80%	87%
85.7%	97%	96%	0%	0%	89%	100%	100%	99%	89%	96%	97%	91%	91%	100%	100%	96%	95%	93%	93%	78%	100%
88.0%	90%	93%	89%	95%	92%	85%	91%	91%	90%	89%	86%	81%	91%	81%	92%	88%	80%	85%	86%	81%	92%
80.0%	84%	83%	77%	74%	78%	69%	83%	77%	78%	84%	79%	82%	82%	87%	83%	81%	79%	84%	83%	78%	76%
75.4%	84%	78%	76%	67%	65%	82%	79%	55%	70%	70%	95%	79%	78%	82%	74%	77%	72%	85%	78%	59%	78%

Model Similarity Dendrogram

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