	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	2nd 82.6%	6th 81.4%	1st 83.8%	3rd 82.5%	7th 81.2%	20th 70.0%	13th 79.3%	10th 80.6%	12th 79.4%	4th 82.1%	11th 79.7%	16th 75.8%	9th 80.6%	14th 76.9%	8th 81.0%	5th 81.6%	19th 74.5%	15th 76.0%	17th 75.4%	18th 75.0%	21st 69.7%
79.5%	87%	85%	86%	92%	81%	65%	71%	71%	81%	83%	74%	77%	87%	75%	86%	88%	84%	65%	77%	74%	81%
76.2%	77%	74%	76%	80%	63%	92%	79%	81%	63%	73%	88%	86%	86%	84%	78%	78%	55%	57%	87%	86%	57%
71.3%	78%	63%	78%	80%	75%	71%	66%	78%	68%	84%	71%	66%	73%	69%	73%	67%	71%	73%	66%	64%	64%
92.3%	95%	91%	95%	96%	90%	89%	96%	92%	94%	95%	92%	94%	94%	86%	95%	92%	96%	86%	91%	88%
89.8%	89%	94%	89%	88%	99%	81%	86%	94%	95%	95%	94%		94%	91%	83%	95%	91%	88%	80%	87%	83%
84.7%	88%	90%	91%	92%	92%	87%	84%	87%	90%	87%	89%	67%	86%	78%	88%	82%	80%	87%	79%	71%	83%
78.7%	87%	84%	91%	85%	86%	67%	78%	86%	85%	77%	81%	95%	74%	80%	71%	70%	68%	82%	80%	63%	63%
78.0%	93%	75%	75%	90%	79%	45%	71%	93%	89%	93%	76%	75%	74%	66%	90%	92%	83%	83%	60%	68%	67%
79.8%	75%	85%	79%	80%	93%	62%	78%	91%	77%	80%	86%	70%	86%	88%	80%	76%	90%	75%	76%	74%	74%
89.7%	94%	93%	91%	94%	87%	93%	93%	89%	88%	96%	87%	97%	92%	86%	90%	89%	75%	77%	91%	91%	91%
81.9%	91%	90%	86%	84%	72%	70%	87%	77%	86%	84%	89%	85%	78%	77%	84%	83%	80%	81%	75%	81%	80%
89.4%	87%	90%	92%	91%	85%	93%	91%	85%	86%	94%	87%	94%	96%	87%	92%	91%	75%	87%	97%		89%
80.3%	75%	88%	76%	77%	81%	77%	83%	85%	84%	77%	88%	76%	89%	86%	80%	82%	83%	82%	77%	86%	54%
81.4%	82%	89%	83%	75%	84%	78%	90%	73%	80%	73%	91%	73%	88%	96%	80%	87%	75%	75%	94%	78%	66%
84.9%	94%	83%	88%	95%	87%	65%	94%	87%	91%	91%	83%	90%	82%	84%	96%	85%	72%	70%	75%	92%	78%
79.7%	83%	90%	89%	90%	76%	60%	70%	89%	75%	87%	79%	75%	92%	69%	87%	93%	78%	89%	75%	64%	64%
60.9%	69%	69%	88%	72%	65%	42%	65%	55%	63%	66%	61%	42%	48%	53%	70%	66%	40%	54%		55%	75%
70.3%	89%	67%	85%	89%	88%	40%	54%	74%	62%	83%	57%	62%	76%	55%	72%	81%	80%	69%	61%	77%	55%
52.2%	51%	43%	49%	48%	63%	46%	57%	53%	52%	52%	51%	44%	49%	48%	73%	77%	55%	42%	44%		46%
83.5%	81%	79%	89%	85%	80%	89%	94%	73%	78%	79%	91%	76%	92%	93%	84%	86%	74%	89%	90%	82%	69%
82.5%	88%	92%	92%	87%	93%	66%	84%	84%	89%	88%	83%	89%	92%	79%	80%	91%	84%	70%	68%	67%	67%
79.9%	81%	81%	84%	87%	88%	67%	84%	78%	86%	84%	84%	88%	84%	81%	74%	85%	80%	79%	67%	79%	57%
73.8%	67%	74%	82%	68%	81%	86%	76%	83%	68%	71%	82%	63%	76%	81%	69%	72%	71%	75%	65%	68%	72%
85.3%	81%	86%	82%	81%	93%	83%	88%	89%	89%	78%	97%	76%	93%	92%	92%	92%	85%	89%	77%	88%	60%
81.2%	77%	88%	84%	73%	86%	80%	85%	71%	82%	77%	94%	83%	86%	92%	75%	82%	75%	83%	91%	78%	63%
72.8%	75%	77%	78%	70%	85%	68%	71%	68%	72%	72%	76%	80%	72%	74%	68%	70%	66%	79%	80%	74%	54%
66.6%	79%	71%	79%	80%	67%	40%	54%	61%	62%	78%	47%	62%	73%	57%	77%	71%	67%	67%	61%	68%	78%
73.7%	92%	79%	88%	83%	90%	52%	78%	88%	83%	92%	67%	67%	75%	57%	90%	90%	54%	56%	54%	58%	54%
73.7%	89%	92%	84%	84%	85%	67%	78%	69%	70%	65%	71%	63%	65%	64%	74%	74%	68%	75%	67%	67%	76%
78.8%	95%	88%	91%	95%	79%	61%	61%	85%	67%	87%		56%	76%		89%	78%	67%		85%	70%	88%
83.3%	92%	89%	94%	96%	93%	70%	91%	88%	89%	89%	78%	92%	90%	77%	77%	74%	77%	91%	64%	74%	65%
76.3%	71%	86%	71%	68%	73%	77%	83%	71%	81%	64%	77%	83%	76%	80%	85%	81%	77%	76%	83%	85%	55%
68.3%	76%	59%		75%	70%	67%	62%	73%	63%	79%	67%	62%	68%	64%	68%	63%	66%	68%		59%	89%
79.1%	77%	81%	82%	74%	69%	80%	86%	81%	84%	77%	91%	75%	84%	74%	69%	74%	84%	78%	76%	81%	85%
80.3%	72%	84%	87%	71%	76%	88%	79%	84%	82%	97%	76%	75%	78%	96%	76%	70%	72%	84%	73%	88%	78%
82.9%	90%	91%	92%	96%	72%	68%	92%	96%	87%	87%	84%	78%	91%	71%	76%	88%	82%	77%	68%	86%	69%
80.1%	84%	85%	84%	90%	83%	64%	83%	80%	83%	87%	76%	85%	80%	74%	87%	90%	73%	78%	75%	80%	61%
85.2%	96%	92%	98%	92%	85%	90%	89%	97%	93%	98%	91%	80%			92%	92%	84%	72%		46%	46%
77.1%	91%	78%	83%	87%	82%	55%	82%	95%	77%	92%	71%	76%	80%	69%	85%	86%	57%	61%	69%	73%	71%
94.5%	97%	91%	94%	91%	97%	100%	94%	94%	96%	87%	100%	94%	99%	97%	99%	95%	99%	99%	94%	91%	77%
76.9%	72%	74%	71%	75%	88%	55%	81%	84%	87%	82%	76%	66%	69%	71%	86%	82%	75%	76%	78%	83%	84%
73.3%	72%	69%	74%	73%	68%	62%	75%	80%	77%	80%	67%	76%	79%	79%	68%	75%	74%	70%	73%	72%	77%
67.4%	73%	70%	70%	70%	63%	53%	69%	54%	59%	72%	79%	69%	65%	71%	73%	72%	60%	79%	72%	60%	62%

Model Similarity Dendrogram

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