	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	6th 75.9%	7th 75.8%	2nd 76.8%	4th 76.3%	14th 73.3%	21st 70.1%	13th 73.8%	11th 74.9%	8th 75.7%	5th 76.1%	19th 72.2%	16th 72.7%	9th 75.7%	12th 74.2%	1st 77.7%	3rd 76.5%	10th 75.6%	20th 71.9%	17th 72.7%	15th 73.3%	18th 72.6%
73.6%	79%	67%	85%	81%	79%	71%	76%	66%	76%	77%	68%	60%	76%	77%	74%	74%	73%	66%	70%	84%	67%
63.3%	52%	73%	60%	65%	40%	66%	71%	62%	71%	62%	55%	65%	72%	89%	81%	71%	62%	44%	65%	56%	48%
59.7%	60%	60%	63%	61%	59%	59%	59%	55%	55%	60%	60%	67%	59%	59%	60%	60%	60%	60%	59%	59%	60%
87.4%	90%	88%	90%	88%	90%	94%	90%	81%	79%	100%	81%	81%	90%	72%	90%	90%	87%	81%	90%	90%	94%
89.8%	93%	91%	100%	100%	84%	89%	89%	87%	97%	84%	89%	89%	89%	89%	78%	84%	95%	89%	89%	89%	91%
88.3%	90%	96%	96%	96%	88%	76%	86%	90%	92%	87%	86%	92%	80%	83%	95%	95%	79%	92%	82%	86%	88%
84.3%	83%	83%	83%	83%	72%	88%	85%	87%	83%	82%	90%	90%	90%	90%	84%	80%	84%	82%	90%	91%	71%
67.8%	66%	73%	66%	66%	76%	51%	62%	69%	62%	74%	64%	70%	74%	59%	77%	76%	75%	65%	55%	72%	71%
73.3%	83%	75%	61%	68%	71%	56%	70%	80%	67%	81%	52%	51%	80%	78%	90%	82%	71%	90%	68%	82%	83%
73.6%	81%	81%	66%	73%	81%	81%	70%	55%	81%	79%	58%	81%	81%	81%	71%	70%	67%	64%	81%	73%	71%
79.5%	90%	87%	89%	90%	84%	77%	84%	87%	84%	68%	73%	87%	84%	74%	74%	77%	69%	63%	74%	79%	76%
70.8%	73%	71%	73%	67%	77%	70%	69%	73%	69%	71%	71%	58%	69%	77%	76%	73%	72%	70%	82%	69%	57%
75.1%	80%	80%	71%	80%	80%	85%	80%	87%	74%	80%	74%	67%	75%	74%	80%	75%	75%	70%	74%	72%	45%
82.6%	81%	84%	81%	81%	70%	89%	82%	90%	80%	86%	82%	90%	94%	91%	82%	80%	81%	88%	83%	70%	69%
71.9%	65%	79%	79%	79%	68%	54%	76%	56%	85%	73%	68%	56%	68%	68%	89%	85%	72%	68%	85%	68%	68%
57.3%	54%	55%	60%	56%	64%	47%	56%	54%	60%	57%	58%	59%	57%	51%	60%	60%	65%	64%	51%	59%	57%
65.5%	66%	71%	81%	73%	91%	64%	61%	46%	66%	71%	66%	62%	57%	71%	66%	66%	62%	41%	61%	56%	77%
77.7%	77%	73%	85%	85%	74%	71%	79%	84%	86%	92%	79%	57%	73%	69%	79%	81%	81%	73%	66%	96%	72%
49.1%	60%	42%	51%	43%	51%	31%	51%	55%	48%	59%	42%	41%	50%	43%	63%	67%	53%	48%	41%	44%	48%
86.5%	94%	69%	92%	92%	88%	91%	84%	94%	96%	89%	68%	81%	91%	88%	81%	84%	88%	84%	90%	88%	85%
72.6%	74%	62%	72%	72%	77%	65%	65%	71%	77%	70%	77%	77%	77%	65%	76%	76%	77%	77%	71%	71%	76%
77.9%	77%	73%	79%	79%	81%	72%	77%	88%	77%	75%	71%	77%	75%	75%	77%	68%	91%	83%	73%		90%
72.0%	70%	71%	78%	65%	73%	76%	73%	78%	81%	81%	78%	53%	76%	87%	68%	78%	87%	63%	70%	53%	53%
75.3%	87%	72%	87%	81%	74%	74%	81%	70%	79%	81%	74%	74%	74%	74%	72%	76%	74%	71%	74%	74%	59%
67.6%	68%	68%	62%	63%	70%	70%	63%	70%	72%	69%	63%	68%	70%	76%	67%	61%	56%	71%	70%	70%	72%
72.0%	73%	92%	72%	72%	77%	72%	74%	75%	73%	63%	77%	66%	66%	74%	73%	78%	56%	58%	75%	88%	57%
69.7%	69%	66%	75%	69%	69%	71%	70%	71%	64%	76%	74%	74%	66%	71%	75%	76%	70%	64%	62%	69%	63%
66.0%	71%	64%	66%	66%	77%	48%	69%	78%	71%	66%	66%	50%	66%	50%	71%	70%	75%	73%	58%	69%	62%
60.5%	62%	81%	73%	72%	67%	50%	59%	54%	53%	53%	53%	53%	53%	62%	69%	73%	49%	57%	59%	53%	65%
70.0%	63%	68%	72%	72%	71%	61%	73%	81%	81%	71%	71%	82%	74%	54%	72%	71%	72%	54%	66%	70%	71%
76.6%	81%	81%	81%	81%	70%	71%	77%	72%	72%	81%	74%	80%	72%	80%	81%	79%	80%	76%	68%	71%	81%
91.5%	98%	98%	94%	88%	84%	84%	100%	87%	84%	98%	84%	90%	90%	90%	98%	98%	98%	84%	90%	87%	98%
84.4%	81%	81%	79%	89%	84%	54%	78%	99%	99%	81%	84%	84%	94%	84%	81%	81%	77%	94%	94%	94%	81%
82.8%	87%	78%	79%	87%	63%	86%	79%	88%	81%	81%	81%	84%	81%	83%	87%	88%	93%	87%	81%	81%	83%
71.0%	66%	75%	90%	82%	32%	68%	52%	64%	72%	67%	55%	90%	82%	66%	79%	74%	87%	75%	75%	58%	83%
70.3%	72%	77%	65%	67%	55%	75%	72%	70%	71%	71%	65%	74%	72%	72%	75%	72%	74%	66%	69%	74%	68%
70.7%	70%	64%	70%	70%	80%	67%	69%	76%	70%	71%	80%	70%	61%	80%	70%	64%	80%	59%	63%	84%	67%
86.1%	88%	85%	81%	89%	100%	89%	83%	88%	89%	89%	89%	89%	89%	85%	91%	85%	85%	88%	89%	49%	88%
75.7%	75%	78%	75%	75%	72%	59%	69%	78%	73%	79%	78%	78%	93%	71%	84%	81%	83%	82%	63%	66%	77%
92.2%	89%	89%	99%	97%	90%	94%	90%	97%	94%	88%	94%	90%	90%	90%	89%	89%	100%	94%	90%	94%	89%
69.4%	72%	73%	72%	70%	73%	70%	72%	72%	69%	72%	60%	60%	73%	63%	72%	65%	69%	74%	59%	70%	78%
75.6%	79%	82%	71%	76%	64%	60%	76%	76%	73%	76%	82%	85%	73%	77%	87%	77%	79%	64%	79%	80%	72%
75.0%	73%	83%	78%	73%	61%	69%	73%	61%	69%	81%	91%	74%	78%	77%	78%	81%	67%	75%	72%	69%	91%

Model Similarity Dendrogram

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