	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	1st 79.7%	8th 77.0%	4th 78.1%	2nd 79.3%	5th 77.9%	21st 66.5%	15th 73.7%	9th 76.9%	14th 73.7%	3rd 78.4%	10th 76.3%	17th 73.3%	6th 77.8%	13th 73.8%	11th 76.2%	7th 77.1%	16th 73.7%	18th 72.4%	19th 71.4%	12th 74.2%	20th 71.2%
79.2%	85%	83%	78%	93%	92%	46%	68%	71%	73%	85%	73%	73%	89%	73%	90%	82%	85%	85%	68%	88%	84%
73.6%	71%	80%	74%	79%	64%	94%	68%	79%	60%	75%	84%	91%	76%	93%	66%	63%	64%	60%	88%	66%	51%
74.7%	76%	66%	76%	80%	76%	68%	66%	86%	63%	80%	72%	72%	72%	68%	74%	75%	76%	81%	58%	97%	87%
81.1%	82%	81%	75%	79%	85%	77%	84%	83%	86%	79%	83%	77%	85%	73%	86%	88%	86%	80%	75%	81%	79%
81.8%	82%	85%	73%	80%		72%	80%	85%	73%	84%	94%	73%	87%	89%	88%	89%	80%	87%	79%	82%	73%
78.6%	79%	81%		80%	82%	83%	80%	92%	79%	80%	79%	79%	81%	76%	77%	75%	71%	79%	75%	65%	78%
83.6%	86%	89%	80%	75%	91%	83%	87%	88%	80%	83%	84%	87%	86%	87%	80%	83%	77%	77%	88%		81%
60.1%	66%	56%	66%	75%	53%	34%	61%	63%	62%	76%	60%	67%	62%	55%	67%	66%	59%	47%	40%	62%	66%
78.4%	84%	83%	81%	81%	77%	48%	64%	80%	62%	90%	84%	66%	84%	72%	88%	83%	98%	84%	71%	80%	86%
80.6%	83%	86%	81%	84%	82%	84%	81%	78%	81%	81%	81%	79%	81%	81%	81%	80%	76%	78%	83%	66%	85%
82.2%	91%	88%	90%	90%	81%	73%	86%	76%	83%	75%	87%	89%	85%	81%	73%		81%	76%	73%	83%
81.3%	82%	84%	81%	81%	82%	79%	84%	86%	84%	84%	75%	77%	82%	86%	88%	82%	79%	72%	76%	78%	86%
78.1%	83%	71%	87%	96%	70%	57%	87%	91%	80%	90%	74%	81%	83%	70%	87%	80%	77%	72%	61%		65%
68.6%	67%	76%	69%	59%	77%	74%	68%	69%	67%	61%	71%	66%	65%	71%	65%	62%	65%	81%	84%	66%	57%
87.5%	87%	88%	84%	85%	93%	86%	90%	78%	90%	87%	93%	89%	91%	93%	83%	86%	90%	86%	81%	88%	89%
70.0%	86%	72%	79%	84%	77%	45%	63%		68%	83%	66%	61%	75%	64%	73%	79%	72%	56%	60%	73%	63%
60.8%	63%	72%	84%	72%	77%	48%	58%	48%	58%	67%	60%	45%	53%	53%	70%	65%	51%	33%	63%	65%	72%
64.2%	77%	61%	78%	81%	70%	34%	49%	63%	60%	72%	54%	54%	71%	50%		74%	73%	73%	59%	62%	69%
47.5%	53%	41%	46%	46%	61%	37%	47%	63%	49%	44%	45%	33%	52%	46%	66%	60%	41%	45%	35%	46%	41%
85.8%	90%	67%	92%	87%	89%	85%	89%	90%	79%	95%	85%	89%	89%	89%	86%	85%	85%	75%	87%	90%	79%
81.4%	87%	87%	79%	84%	84%	59%	91%	90%	84%	87%	84%	84%	85%	78%	78%	90%	78%	69%	58%	84%	90%
78.5%	92%	79%	80%	89%	88%	47%	85%	96%	83%	91%	74%	86%	82%	68%	72%	88%	60%	71%	51%	86%	80%
78.0%	70%	78%	82%	78%	84%	81%	80%	78%	76%	70%	81%	77%	76%	82%	76%	78%	81%	80%	82%	76%	71%
76.0%	78%	71%	75%	78%	81%	72%	81%	79%	83%	78%	76%	71%	82%	82%	79%	80%	80%	73%	66%	70%	62%
68.9%	69%	76%	77%	63%	76%	74%	70%	71%	63%	63%	80%	76%	66%	76%	68%	71%	60%	58%	81%	54%	55%
68.0%	76%	70%	75%	67%	76%	57%	60%	71%	63%	66%	68%	73%	69%	67%	69%	75%	65%	67%		71%	56%
79.4%	86%	83%	87%	83%	84%	50%	71%	90%	77%	89%	69%	73%	88%	67%	88%	81%	87%	78%	75%	81%	81%
72.1%	78%	71%	66%	76%	84%	50%	73%	82%	78%	82%	69%	78%	72%	55%	80%	76%	70%	65%	59%	77%
77.7%	95%	87%	89%	87%	88%	70%	78%	70%	74%	72%	71%	71%	76%	69%	82%	76%	74%	75%	74%	76%	78%
75.0%	78%	82%	77%	85%	82%	54%	61%	78%	84%	78%	74%	54%	87%	75%	82%	82%	80%	66%	74%	63%	79%
64.6%	69%	70%	62%	62%	68%	91%	64%	53%	67%	42%	83%	62%	64%	81%	36%	52%	81%	76%	81%	64%	28%
70.0%	69%	80%	69%	65%	69%	78%	80%	59%	82%	65%	73%	73%	73%	78%	66%	71%	69%	64%	88%	50%	50%
75.7%	87%	66%	76%	80%	76%	68%	66%	86%	63%	80%	72%	72%	72%	68%	74%	74%	76%	81%	58%	97%	97%
78.4%	83%	77%	78%	79%	66%	73%	81%	81%	83%	83%	84%	78%	81%	72%	80%	82%	85%	82%	73%	71%	75%
64.0%	80%	75%	76%	82%	61%	59%	51%	48%	66%	70%	57%	54%	75%	62%	54%	52%	63%	60%	77%	57%	64%
74.7%	79%	79%	77%	80%	74%	64%	76%	84%	75%	78%	77%	68%	77%	68%	72%	75%	78%	77%	66%	71%	74%
81.2%	90%	87%	83%	82%	92%	90%	80%	67%	80%	73%	97%	86%	89%	89%	52%	78%	84%	85%	85%	84%	52%
82.1%	73%	88%	82%		76%	84%	71%	82%	70%	92%	84%	83%	74%	83%	91%	91%	78%	74%	91%	93%
71.0%	85%	66%	73%	83%	69%	57%	83%	80%	78%	86%	65%	70%	75%	62%	79%	77%	46%	59%	51%	67%	80%
89.8%	95%	83%	94%	98%	94%	85%	83%	96%	81%	98%	90%	90%	90%	85%	93%	93%	94%	99%	74%	85%	85%
72.7%	80%	75%	77%	77%	78%	72%	80%	76%	76%	80%	77%	71%	80%	72%	78%	78%	22%	67%	66%	87%	57%
79.4%	84%	89%	80%	85%	75%	56%	77%	84%	75%	88%	84%	76%	83%	89%	82%	79%	84%	81%	84%	72%	61%
77.1%	71%	82%	91%	82%	67%	61%	66%	61%	71%	88%	86%	79%	79%	76%	82%	83%	86%	79%	80%	69%	81%

Model Similarity Dendrogram

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