	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	3rd 78.9%	7th 76.7%	2nd 79.6%	1st 80.1%	16th 74.4%	21st 70.2%	15th 75.2%	13th 75.4%	10th 76.4%	6th 77.0%	12th 75.5%	19th 72.9%	8th 76.7%	18th 73.1%	4th 78.9%	5th 78.6%	14th 75.3%	20th 71.4%	17th 73.3%	9th 76.6%	11th 76.0%
69.2%	65%	65%	73%	71%	73%	73%	73%	68%	80%	70%	74%	72%	74%	73%	70%	64%	64%	49%	69%		64%
66.0%	68%	67%	65%	67%	63%	65%	68%	61%	74%	68%	67%	48%	71%	61%	70%	68%	69%	67%	64%	69%	66%
73.0%	67%	67%	79%	67%	79%	79%	67%	70%	58%	67%	79%	79%	90%	79%	67%	67%	67%	79%	79%	79%	67%
87.3%	86%	90%	89%	94%	70%	87%	89%	81%	84%	89%	94%	95%	92%	85%	76%	85%	90%	80%	95%	95%	87%
84.0%	83%	81%	83%	88%	81%	81%	88%	88%	88%	92%	81%	81%	81%	81%	89%	92%	84%	84%	81%	83%	74%
86.0%	95%	90%	96%	93%	89%	69%	84%	86%	87%	84%	90%	93%	87%	77%	87%	93%	80%	73%	89%	78%	87%
80.8%	89%	82%	86%	90%	86%	73%	72%	89%	87%	75%	64%	81%	72%	60%	79%	90%	81%	87%	79%	79%	95%
71.4%	75%	67%	69%	76%	68%	48%	63%	78%	70%	78%	77%	68%	67%	66%	85%	85%	79%	68%	71%	68%	73%
84.5%	77%	71%	91%	98%	88%	72%	76%	83%	80%	89%	92%	84%	92%	91%	81%	82%	90%	81%	86%	87%	83%
92.8%	95%	85%	96%	94%	95%	95%	88%	75%	92%	100%	95%	96%	95%	95%	92%	96%	90%	89%	95%	95%	96%
76.0%	78%	90%	92%	81%	86%	76%	87%	74%	77%	67%	83%	87%	67%	58%	85%	78%	60%	46%	80%	92%	52%
81.8%	100%	86%	86%	86%	86%	74%	84%	87%	85%	79%	87%	86%	78%	71%	83%	78%	69%	63%	85%	78%	86%
74.1%	76%	81%	80%	82%	77%	74%	78%	77%	73%	72%	71%	64%	76%	64%	70%	78%	66%	70%	75%	74%	78%
76.6%	80%	76%	77%	80%	84%	80%	74%	78%	73%	76%	83%	60%	80%	75%	79%	78%	75%	66%	78%	85%	72%
79.5%	78%	76%	76%	82%	79%	81%	76%	79%	79%	80%	82%	78%	77%	85%	80%	84%	81%	79%	78%	82%	78%
81.5%	84%	72%	85%	84%	87%	74%	76%	84%	85%	90%	84%	83%	91%	90%	84%	78%	75%	80%	70%	72%	84%
67.0%	62%	71%	81%	81%	71%	65%	60%	46%	75%	65%	69%	64%	51%	60%	69%	69%	64%	68%	77%	68%	71%
75.7%	80%	72%	75%	75%	82%	71%	67%	79%	74%	69%	74%	82%	73%	79%	74%	75%	82%	87%	64%	81%	75%
60.1%	70%	62%	54%	47%	64%	40%	46%	55%	55%	59%	42%	34%	70%	65%	77%	92%	87%	43%	34%	82%	84%
75.2%	74%	80%	79%	79%	84%	62%	75%	76%	77%	74%	80%	60%	74%	74%	80%	76%	75%	70%	80%	75%	76%
76.3%	91%	72%	80%	83%	87%	68%	73%	75%	74%	80%	68%	71%	81%	73%	87%	78%	75%	70%	67%	73%	77%
76.0%	77%	83%	73%	81%	72%	79%	78%	79%	77%	76%	74%	71%	72%	70%	74%	81%	75%	70%	74%	81%	78%
73.0%	69%	73%	76%	75%	79%	71%	78%	79%	76%	85%	78%	63%	68%	75%	66%	76%	72%	73%	67%	71%	63%
66.0%	67%	63%	70%	74%	64%	71%	71%	69%	63%	68%	64%	64%	64%	64%	62%	62%	72%	61%	64%	64%	64%
78.2%	77%	82%	86%	84%	74%	79%	86%	71%	78%	84%	89%	56%	77%	71%	92%	81%	91%	65%	79%	84%	56%
68.5%	77%	82%	70%	70%	73%	56%	75%	66%	70%	62%	75%	79%	57%	57%	75%	63%	59%	51%	81%	74%	67%
73.9%	83%	63%	86%	76%	76%	67%	73%	81%	77%	76%	60%	62%	73%	76%	83%	80%	83%	64%	70%	60%	83%
73.2%	77%	73%	78%	78%	75%	56%	69%	82%	78%	76%	63%	62%	77%	64%	90%	78%	64%	81%	72%	69%	76%
74.7%	76%	85%	83%	83%	76%	77%	79%	62%	76%	69%	78%	76%	68%	68%	81%	80%	64%	65%	74%	76%	72%
70.3%	86%	71%	77%	77%	74%	54%	60%	78%	69%	66%	68%	75%	79%	66%	76%	67%	64%	61%	73%	66%	69%
69.7%	70%	70%	70%	70%	67%	64%	70%	64%	73%	73%	66%	66%	69%	66%	70%	72%	73%	66%	78%	73%	73%
46.9%	46%	46%	44%	49%	45%	45%	51%	52%	55%	46%	46%	37%	46%	45%	46%	46%	46%	46%	55%	46%	46%
80.0%	78%	78%	89%	85%	89%	89%	66%	70%	66%	78%	89%	89%	89%	89%	78%	78%	78%	89%	45%	89%	78%
70.9%	77%	67%	74%	83%	76%	67%	59%	78%	70%	76%	64%	60%	77%	65%	83%	69%	71%	75%	60%	67%	71%
81.1%	85%	78%	81%	89%	47%	86%	77%	84%	87%	81%	84%	84%	84%	86%	85%	81%	86%	83%	64%	81%	91%
77.1%	77%	83%	74%	70%	70%	79%	83%	73%	85%	76%	72%	78%	78%	80%	71%	81%	81%	77%	73%		81%
77.4%	84%	85%	88%	84%	66%	83%	88%	71%	80%	86%	66%	79%	82%	65%	82%	82%	72%	62%	80%	66%	74%
86.4%	92%	93%	85%	85%	76%	77%	91%	91%	88%	95%	86%	81%	88%	81%	94%	91%	81%	86%	81%	85%	87%
75.8%	83%	78%	85%	81%	79%	66%	80%	80%	73%	80%	76%	77%	77%	66%	76%	79%	74%	70%	67%	73%	71%
85.7%	88%	89%	90%	97%	55%	55%	89%	86%	80%	93%	81%	79%	93%	89%	92%	92%	92%	89%	89%	89%	92%
85.2%	95%	95%	93%	93%	61%	66%	91%	93%	90%	85%	77%	76%	93%	76%	91%	95%	89%	81%	71%	87%	91%
76.6%	80%	82%	79%	80%	73%	51%	79%	79%	71%	74%	82%	82%	75%	82%	84%	79%	78%	79%	68%	70%	82%
74.5%	77%	74%	80%	81%	54%	75%	76%	67%	78%	81%	71%	74%	71%	79%	76%	79%	68%	79%	73%	76%

Model Similarity Dendrogram

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