	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	4th 74.9%	5th 74.7%	2nd 75.2%	1st 75.9%	17th 70.9%	16th 71.6%	6th 74.7%	20th 70.5%	14th 72.0%	3rd 75.0%	9th 73.6%	12th 72.6%	10th 73.2%	11th 73.0%	7th 74.2%	8th 74.0%	18th 70.8%	21st 64.8%	19th 70.7%	13th 72.3%	15th 71.7%
75.1%	71%	75%	75%	86%	78%	63%	79%	70%	70%	75%	79%	70%	70%	75%	83%	75%	70%	68%	76%	79%	90%
71.5%	71%	64%	71%	90%	38%	72%	62%	68%	63%	84%	80%	80%	71%	72%	82%	71%	74%	65%	81%	71%	71%
53.1%	51%	50%	44%	48%	44%	55%	61%	51%	44%	56%	63%	61%	56%	56%	47%	45%	57%	47%	47%	81%	51%
90.3%	90%	81%	90%	80%	100%	94%	100%	90%	90%	100%	100%	81%	100%	100%	81%	90%	94%	83%	90%	81%	81%
78.5%	81%	72%	86%	81%	87%	86%	88%	80%	80%	65%	73%	76%	73%	71%	86%	73%	66%	74%	81%	73%	96%
89.5%	96%	97%	96%	96%	85%	95%	88%	88%	86%	88%	95%	92%	82%	92%	88%	87%	65%	95%	95%	86%	88%
82.3%	79%	84%	79%	83%	82%	85%	88%	88%	87%	85%	80%	82%	85%	82%	85%	85%	83%	75%	85%	82%	64%
73.3%	77%	76%	78%	78%	73%	58%	78%	71%	74%	78%	69%	76%	77%	71%	77%	73%	69%	60%	65%	74%	87%
73.6%	81%	70%	70%	67%	76%	47%	65%	65%	65%	79%	79%	75%	82%	78%	81%	81%	89%	60%	65%	85%	85%
73.8%	81%	71%	81%	73%	81%	81%	70%	60%	81%	73%	58%	81%	81%	81%	71%	71%	65%	54%	81%	81%
79.2%	81%	86%	87%	90%	81%	87%	84%	74%	80%	68%	90%	87%	74%	75%	74%	75%	67%	59%	76%	90%	79%
68.6%	70%	71%	73%	71%	52%	73%	69%	73%	73%	71%	69%	58%	66%	77%	73%	69%	69%	73%	58%	73%	60%
73.4%	72%	79%	85%	84%	68%	84%	72%	64%	72%	81%	77%	69%	78%	77%	68%	75%	61%	68%	72%	68%	68%
80.6%	63%	78%	63%	75%	88%	90%	78%	78%	78%	78%	91%	88%	78%	88%	82%	84%	78%	77%	82%	88%	88%
72.5%	73%	77%	77%	90%	74%	78%	73%	62%	73%	84%	76%	62%	73%	73%	73%	76%	56%	57%	76%	72%	68%
65.7%	75%	70%	66%	72%	72%	61%	67%	67%	65%	70%	53%	65%	65%	63%	73%	70%	70%	45%	61%	65%	64%
60.2%	64%	70%	73%	57%	54%	50%	61%	51%	60%	60%	64%	55%	48%	66%	73%	66%	61%	52%	61%	64%	55%
75.3%	74%	78%	75%	74%	80%	64%	80%	73%	73%	80%	79%	73%	73%	75%	79%	78%	55%	73%	78%	81%	86%
49.3%	57%	42%	51%	42%	63%	42%	51%	48%	58%	56%	40%	33%	51%	31%	56%	63%	54%	40%	41%	63%	53%
86.5%	92%	89%	92%	92%	81%	90%	89%	81%	81%	92%	82%	81%	89%	81%	92%	92%	80%	74%	90%	86%	90%
66.7%	70%	71%	69%	70%	72%	61%	70%	61%	71%	71%	71%	71%	71%	67%	60%	67%	65%	51%	56%	76%	59%
80.4%	91%	91%	89%	77%	88%	64%	89%	91%	91%	79%	67%	86%	91%	67%	89%	85%	77%	75%	53%	83%	65%
78.0%	70%	89%	78%	65%	79%	84%	81%	80%	68%	78%	79%	90%	78%	87%	65%	71%	92%	67%	92%		67%
69.8%	77%	79%	77%	85%	74%	72%	67%	63%	67%	74%	76%	67%	69%	69%	61%	72%	61%	61%	72%	61%	61%
69.8%	73%	63%	63%	69%	63%	73%	63%	73%	69%	63%	63%	79%	69%	79%	79%	72%	76%	71%	69%	63%	74%
67.9%	71%	71%	76%	76%	70%	70%	70%	58%	58%	75%	75%	66%	66%	74%	64%	77%	55%	65%	67%	74%	48%
63.9%	69%	70%	72%	69%	59%	58%	67%	59%	59%	70%	62%	59%	59%	68%	68%	64%	64%	62%	64%	59%	60%
64.6%	66%	67%	60%	72%	68%	57%	71%	61%	61%	71%	67%	61%	67%	58%	63%	66%	70%	60%	49%	65%	77%
62.2%	69%	73%	73%	80%	80%	50%	72%	56%	59%	55%	59%	49%	53%	52%	72%	62%	53%	57%	59%	62%	62%
75.2%	69%	74%	78%	78%	63%	64%	71%	82%	78%	80%	75%	78%	75%	77%	78%	80%	85%	70%	74%	79%	71%
61.0%	64%	66%	69%	69%	65%	55%	63%	61%	65%	65%	61%	58%	61%	61%	55%	65%	61%	51%	55%	54%	58%
81.3%	81%	80%	73%	77%	73%	86%	93%	81%	73%	87%	95%	93%	87%	87%	76%	74%	88%	76%	76%	65%	87%
91.9%	97%	95%	88%	93%	88%	98%	91%	97%	88%	97%	89%	91%	97%	97%	91%	89%	96%	91%	91%	68%	97%
84.8%	93%	83%	87%	87%	72%	79%	80%	92%	91%	82%	86%	81%	81%	85%	87%	87%	86%	92%	76%	81%	93%
70.6%	67%	75%	82%	82%	32%	65%	63%	63%	79%	67%	55%	79%	64%	64%	79%	83%	93%	71%	75%	63%	82%
66.5%	62%	70%	71%	69%	59%	78%	71%	59%	66%	63%	73%	69%	73%	69%	69%	65%	59%	49%	69%	67%	67%
58.5%	59%	62%	66%	66%	55%	65%	60%	52%	62%	66%	55%	61%	55%	53%	66%	59%	61%	39%	49%	62%	56%
72.0%	83%	76%	77%	83%	85%	76%	88%	87%	83%	83%	71%	60%	83%	62%	73%	76%	61%	50%	72%	41%	41%
66.0%	72%	69%	73%	73%	67%	60%	70%	67%	73%	74%	68%	58%	73%	58%	62%	72%	51%	53%	59%	71%	63%
90.0%	91%	89%	83%	87%	83%	96%	97%	91%	83%	97%	95%	97%	97%	97%	85%	84%	98%	85%	85%	85%	85%
67.4%	72%	66%	68%	72%	58%	81%	63%	64%	62%	72%	66%	72%	69%	67%	72%	67%	64%	61%	68%	72%	59%
75.3%	83%	82%	76%	71%	82%	59%	75%	75%	71%	69%	82%	77%	75%	80%	78%	75%	73%	69%	75%	79%	75%
69.1%	73%	72%	73%	64%	56%	71%	73%	57%	64%	64%	78%	73%	61%	77%	73%	73%	72%	61%	72%	64%	81%

Model Similarity Dendrogram

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