	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	3rd 77.9%	2nd 78.3%	4th 77.7%	1st 78.5%	15th 71.7%	17th 70.6%	11th 73.7%	10th 74.1%	9th 74.7%	6th 76.8%	8th 74.8%	18th 70.0%	12th 73.5%	13th 73.3%	7th 75.8%	5th 76.8%	16th 71.3%	21st 65.9%	14th 73.2%	20th 69.0%	19th 70.0%
83.2%	90%	87%	81%	90%	82%	74%	90%	89%	86%	90%	89%	82%	82%	92%	88%	92%	76%	53%	91%	72%	71%
77.6%	82%	81%	87%	81%	56%	80%	78%	80%	65%	80%	74%	76%	83%	81%	73%	82%	83%	64%	86%	76%	81%
66.6%	72%	66%	59%	59%	59%	72%	69%	68%	59%	74%	76%	79%	59%	72%	62%	70%	67%	63%	61%	66%	66%
73.3%	73%	69%	73%	74%	77%	66%	77%	73%	78%	73%	73%	74%	78%	69%	77%	79%	68%	68%	70%	76%	74%
83.9%	89%	90%	94%	93%	91%	90%	88%	81%	85%	83%	81%	76%	75%	88%	80%	84%	83%	66%	94%	66%	84%
90.5%	94%	95%	94%	94%	96%	86%	91%	86%	96%	94%	96%	81%	85%	90%	86%	88%	91%	92%	91%	86%	89%
75.9%	73%	79%	71%	77%	61%	76%	77%	84%	83%	72%	81%	79%	80%	81%	75%	85%	81%	80%	70%	48%	80%
75.0%	82%	78%	74%	81%	68%	52%	80%	74%	76%	77%	67%	73%	78%	71%	86%	78%	71%	80%	70%	78%	81%
80.7%	79%	79%	76%	76%	81%	72%	80%	76%	88%	89%	85%	75%	81%	80%	74%	70%	83%	94%	80%	94%	83%
75.0%	74%	84%	84%	77%	74%	74%	68%	76%	74%	75%	74%	74%	77%	74%	81%	80%	78%	61%	74%	74%	69%
69.6%	74%	75%	71%	75%	68%	68%	71%	71%	79%	73%	71%	75%	66%	77%	67%	68%	65%	56%	64%	75%	53%
75.0%	85%	79%	77%	79%	77%	79%	77%	76%	74%	67%	79%	78%	64%	66%	78%	77%	73%	68%	77%	76%	70%
68.3%	70%	74%	79%	86%	75%	79%	58%	63%	67%	70%	74%	58%	62%	67%	71%	70%	58%	58%	79%	58%	58%
76.4%	74%	78%	74%	77%	80%	84%	73%	81%	79%	84%	76%	63%	82%	64%	75%	73%	76%	73%	78%	84%	76%
59.2%	64%	66%	67%	60%	55%	56%	67%	70%	62%	61%	58%	61%	59%	51%	63%	55%	64%	47%	50%	47%	61%
68.6%	75%	73%	77%	74%	79%	57%	69%	73%	70%	78%	61%	67%	71%	66%	67%	66%	71%	64%	67%	69%	47%
77.0%	86%	90%	86%	78%	92%	80%	76%	58%	83%	74%	82%	65%	73%	75%	78%	89%	59%	54%	86%	76%	78%
59.5%	71%	70%	64%	64%	65%	41%	57%	74%	60%	58%	60%	64%	66%	56%	67%	65%	67%	58%	55%	33%	35%
73.7%	87%	68%	86%	82%	34%	56%	80%	94%	88%	92%	68%	47%	90%	81%	66%	82%	74%	58%	57%	89%	69%
68.0%	79%	77%	76%	76%	83%	57%	78%	66%	57%	74%	62%	57%	72%	62%	78%	74%	53%	59%	67%	57%	64%
73.4%	72%	77%	79%	82%	79%	73%	71%	72%	72%	85%	70%	65%	75%	77%	68%	68%	60%	65%	73%	85%	74%
83.0%	84%	87%	80%	80%	81%	84%	83%	84%	82%	85%	81%	72%	87%	93%	86%	90%	85%	75%	83%	86%	75%
76.8%	78%	87%	80%	79%	75%	82%	79%	77%	84%	79%	85%	69%	67%	69%	78%	79%	77%	75%	73%	71%	70%
64.5%	76%	74%	75%	86%	65%	72%	57%	64%	61%	69%	74%	43%	61%	60%	66%	68%	57%	33%	69%	57%	67%
79.0%	76%	86%	85%	82%	81%	76%	83%	78%	85%	84%	85%	70%	73%	63%	81%	84%	77%	85%	79%	82%	65%
60.3%	55%	73%	61%	66%	71%	60%	48%	55%	59%	69%	69%	51%	53%	73%	58%	63%	49%	78%	63%	65%	28%
67.8%	74%	72%	71%	69%	73%	53%	64%	71%	70%	71%	58%	66%	72%	68%	77%	71%	70%	48%	68%	71%	66%
63.7%	70%	69%	66%	66%	74%	45%	63%	69%	75%	61%	58%	53%	59%	53%	78%	69%	68%	66%	53%	55%	68%
76.7%	89%	84%	85%	85%	87%	73%	76%	69%	79%	80%	70%	70%	70%	70%	73%	79%	76%	77%	70%		73%
74.3%	85%	78%	79%	87%	86%	52%	67%	84%	78%	78%	80%	80%	75%	64%	80%	80%	80%	53%	71%	54%	70%
77.0%	86%	81%	86%	84%	77%	72%	79%	75%	74%	79%	74%	71%	77%	71%	81%	78%	68%	70%	74%	75%	84%
74.1%	69%	75%	82%	82%	82%	69%	72%	73%	82%	67%	65%	62%	82%	69%	79%	71%	69%	78%	80%	73%	75%
65.9%	72%	66%	59%	59%	59%	72%	69%	68%	59%	74%	76%	79%	59%	72%	59%	70%	66%	59%	61%	59%	66%
70.4%	79%	65%	79%	90%	64%	58%	66%	73%	70%	72%	67%	57%	68%	67%	79%	84%	71%	85%	56%	59%	69%
80.7%	84%	87%	81%	88%	37%	91%	78%	78%	77%	79%	82%	92%	82%	86%	93%	89%	78%	76%	72%	90%	74%
61.3%	67%	65%	68%	62%	51%	69%	63%	69%	59%	61%	65%	60%	59%	60%	61%	63%	63%	51%	62%	55%	55%
79.9%	84%	80%	90%	91%	74%	80%	78%	70%	83%	88%	78%	78%	83%	83%	82%	85%	77%	58%	80%	74%	82%
86.0%	90%	91%	90%	90%	81%	90%	80%	90%	90%	91%	87%	75%	90%	91%	97%	92%	71%	84%	94%	61%	81%
71.2%	77%	76%	82%	84%	75%	66%	75%	63%	70%	83%	79%	69%	73%	68%	73%	74%	58%	41%	68%	66%	75%
94.5%	94%	100%	93%	93%	93%	94%	97%	98%	93%	91%	90%	87%	93%	94%	99%	96%	94%	97%	95%		99%
75.3%	82%	82%	82%	82%	41%	71%	78%	80%	74%	84%	82%	81%	81%	81%	79%	84%	77%	22%	81%	74%	84%
57.9%	63%	62%	59%	59%	59%	52%	62%	56%	50%	63%	57%	62%	54%	63%	62%	54%	60%	54%	57%	53%	54%
79.9%	71%	90%	81%	77%	65%	81%	79%	59%	76%	70%	97%	94%	86%	96%	80%	85%	72%	89%	97%	66%	66%

Model Similarity Dendrogram

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