	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	2nd 79.0%	4th 78.1%	1st 79.3%	10th 75.7%	11th 75.7%	15th 75.1%	5th 77.4%	13th 75.5%	14th 75.4%	3rd 78.1%	12th 75.6%	19th 72.4%	17th 75.0%	9th 75.9%	8th 76.4%	6th 76.8%	20th 72.3%	21st 70.6%	7th 76.5%	16th 75.0%	18th 74.6%
80.4%	80%	79%	84%	81%	76%	74%	89%	82%	85%	85%	85%	79%	73%	85%	80%	77%	69%	87%	84%	80%	75%
70.6%	73%	74%	77%	73%	44%	78%	71%	65%	58%	72%	75%	72%	75%	77%	74%	76%	71%	65%	77%	69%	66%
63.1%	71%	65%	58%	0%	62%	71%	68%	66%	58%	73%	71%	71%	70%	65%	58%	68%	68%	62%	60%	66%	74%
79.0%	86%	72%	86%	78%	86%	70%	81%	86%	82%	81%	76%	75%	79%	78%	81%	84%	76%	74%	77%	80%	70%
88.3%	95%	92%	95%	97%	91%	93%	99%	87%	90%	92%	86%	80%	87%	86%	91%	74%	90%	65%	91%	90%	83%
85.8%	78%	88%	78%	84%	86%	94%	86%	95%	90%	86%	90%	80%	88%	83%	78%	78%	93%	95%	82%	84%	86%
82.3%	79%	77%	74%	84%	81%	77%	77%	84%	95%	86%	77%	87%	76%	92%	87%	90%	49%	93%	77%	94%	92%
77.9%	83%	84%	79%	78%	78%	60%	79%	81%	80%	82%	81%	78%	80%	76%	81%	81%	69%	58%	78%	85%	85%
68.2%	65%	67%	64%	66%	84%	72%	74%	74%	78%	70%	70%	57%	69%	64%	61%	61%	72%	77%	78%	55%	55%
76.0%	77%	85%	85%	85%	75%	75%	77%	72%	75%	76%	75%	75%	75%	75%	74%	79%	59%	73%	75%	75%	79%
62.5%	72%	67%	74%	72%	65%	70%	59%	76%	61%	55%	59%	68%	48%	49%	62%	58%	38%	30%	79%	70%	81%
88.4%	81%	86%	91%	88%	85%	87%	89%	100%	93%	91%	91%	85%	78%	93%	89%	83%	92%	90%	85%		91%
64.8%	69%	70%	75%	75%	72%	74%	66%	54%	61%	63%	69%	64%	66%	71%	61%	60%	55%	55%	71%	55%	55%
70.9%	67%	67%	63%	67%	70%	77%	70%	66%	67%	72%	77%	75%	65%	69%	76%	67%	80%	68%	78%	77%	70%
79.5%	87%	78%	82%	82%	74%	82%	85%	70%	78%	83%	78%	78%	78%	82%	73%	80%	81%	85%	79%	74%	80%
75.1%	80%	74%	79%	74%	74%	70%	79%	78%	75%	77%	77%	80%	78%	76%	79%	73%	73%	62%	74%		70%
81.9%	91%	87%	91%	89%	84%	70%	80%	65%	81%	82%	87%	76%	75%	78%	86%	88%	80%	75%	86%	84%	84%
76.0%	79%	77%	83%	86%	94%	53%	72%	75%	77%	77%	63%	77%	81%	63%	86%	78%	82%	58%	77%	77%	82%
55.7%	58%	42%	57%	45%	66%	42%	46%	66%	64%	67%	43%	37%	63%	63%	76%	69%	67%	51%	33%	71%	43%
77.8%	88%	86%	85%	85%	90%	70%	84%	75%	74%	85%	73%	67%	81%	68%	83%	85%	68%	63%	75%	71%	78%
77.4%	81%	82%	81%	83%	76%	84%	79%	74%	80%	81%	78%	71%	79%	92%	57%	74%	63%	70%	88%	83%	70%
72.2%	68%	73%	76%	77%	61%	81%	73%	66%	73%	72%	84%	82%	70%	79%	77%	74%	63%	60%	75%	67%	65%
75.0%	68%	68%	72%	68%	77%	92%	80%	84%	69%	79%	80%	83%	83%	91%	70%	69%	70%	67%	86%	59%	60%
59.6%	69%	67%	72%	66%	57%	76%	54%	55%	56%	62%	63%	41%	58%	59%	61%	59%	52%	52%	68%	52%	52%
76.6%	79%	81%	77%	81%	80%	83%	80%	79%	79%	79%	75%	66%	76%	70%	76%	80%	79%	69%	78%	68%	74%
65.7%	63%	80%	75%	71%	56%	82%	72%	66%	62%	67%	76%	67%	60%	83%	58%	58%	53%	52%	74%	53%	52%
80.6%	79%	80%	83%	85%	77%	67%	84%	80%	72%	89%	66%	83%	74%	69%	86%	92%	88%	85%	82%	85%	86%
73.7%	79%	79%	74%	77%	50%	68%	77%	76%	68%	79%	77%	72%	75%	71%	76%	71%	83%	71%	68%	85%	72%
71.9%	85%	96%	96%	82%	81%	66%	73%	69%	68%	58%	71%	55%	58%	60%	69%	70%	61%	71%	75%	74%	71%
80.7%	85%	80%	81%	98%	95%	71%	72%	78%	78%	86%	85%	75%	77%	74%	84%	83%	81%	71%	80%	78%	83%
75.2%	83%	73%	76%	77%	81%	78%	69%	67%	70%	82%	78%	76%	74%	78%	78%	81%	64%	66%	73%	78%	78%
92.7%	88%	94%	98%	98%	97%	88%	91%	93%	98%	86%	88%	88%	89%	94%	94%	90%	91%	98%	100%	98%	85%
70.6%	76%	70%	63%	63%	67%	76%	73%	71%	63%	78%	76%	76%	75%	70%	64%	74%	73%	67%	65%	63%	79%
73.9%	86%	75%	77%	85%	76%	69%	72%	83%	75%	76%	67%	64%	71%	65%	78%	78%	75%	72%	67%	67%	74%
76.5%	92%	90%	90%	88%	48%	74%	78%	74%	74%	66%	65%	66%	77%	72%	82%	80%	86%	72%	83%	79%	71%
80.0%	90%	86%	89%	90%	65%	80%	83%	79%	73%	87%	83%	78%	79%	83%	79%	89%	74%	69%	74%	75%	76%
69.9%	72%	70%	72%	73%	68%	73%	74%	64%	66%	72%	70%	66%	73%	70%	69%	73%	67%	66%	68%	68%	73%
81.4%	94%	82%	88%	88%	85%	87%	96%	86%	88%	91%	73%	71%	88%	74%	73%	83%	61%	74%	76%	64%	88%
77.6%	76%	84%	82%	83%	80%	78%	80%	75%	79%	86%	80%	70%	79%	82%	77%	81%	62%	64%	70%	81%	80%
87.8%	88%	94%	98%	0%	97%	88%	91%	93%	98%	86%	88%	88%	89%	94%	91%	90%	91%	97%	100%	98%	85%
74.0%	72%	76%	66%	66%	83%	61%	75%	77%	81%	81%	70%	54%	75%	68%	80%	80%	76%	73%	70%	87%	84%
74.6%	76%	76%	70%	75%	78%	57%	83%	69%	66%	72%	76%	76%	69%	83%	85%	79%	83%	84%	67%	68%	74%
86.1%	90%	84%	96%	93%	83%	92%	88%	73%	84%	88%	80%	86%	93%	88%	87%	87%	83%	80%	86%	89%	78%

Model Similarity Dendrogram

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