	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 78.1%	4th 77.4%	3rd 78.1%	1st 78.3%	10th 74.3%	17th 71.1%	12th 74.1%	13th 74.0%	11th 74.2%	6th 76.3%	9th 74.6%	19th 70.0%	8th 74.7%	16th 72.3%	7th 76.0%	5th 76.8%	15th 72.4%	20th 68.6%	14th 73.1%	18th 70.5%	21st 67.5%
84.3%	92%	85%	81%	95%	82%	72%	94%	85%	85%	92%	89%	82%	82%	86%	90%	91%	79%	73%	84%	84%	68%
78.5%	84%	78%	87%	81%	53%	84%	83%	77%	70%	82%	74%	73%	83%	80%	81%	84%	81%	69%	82%	81%	81%
67.7%	67%	66%	72%	59%	59%	72%	69%	68%	59%	74%	76%	82%	67%	72%	69%	66%	66%	63%	63%	66%	66%
73.4%	77%	69%	76%	74%	79%	66%	73%	80%	78%	73%	73%	74%	78%	69%	77%	77%	68%	69%	70%		68%
84.0%	97%	90%	94%	93%	91%	98%	91%	78%	81%	75%	81%	80%	88%	85%	76%	82%	83%	60%	94%	70%	78%
91.3%	94%	95%	94%	94%	89%	96%	91%	83%	96%	88%	96%	92%	85%	91%	88%	88%	98%	98%	94%	78%	89%
78.6%	78%	79%	71%	77%	72%	80%	77%	84%	79%	79%	80%	79%	80%	81%	80%	85%	75%	83%	70%	88%	74%
74.5%	87%	80%	74%	81%	70%	54%	76%	74%	77%	81%	78%	71%	78%	71%	85%	79%	78%	69%	70%	69%	62%
79.4%	78%	80%	76%	76%	80%	75%	76%	91%	91%	83%	82%	76%	81%	80%	76%	70%	77%	94%	80%	86%	59%
76.4%	80%	74%	84%	77%	74%	74%	71%	69%	76%	80%	81%	74%	75%	74%	80%	95%	76%	60%	74%	74%	82%
71.5%	74%	74%	75%	75%	79%	76%	68%	75%	74%	69%	71%	75%	68%	77%	64%	72%	59%	61%	64%	74%	77%
74.9%	85%	79%	77%	77%	77%	79%	77%	77%	77%	60%	73%	78%	71%	66%	80%	73%	73%	70%	77%	74%	72%
68.9%	68%	74%	79%	86%	71%	79%	69%	62%	65%	70%	74%	58%	71%	79%	69%	75%	58%	50%	73%	58%	58%
76.4%	70%	78%	74%	73%	80%	79%	73%	82%	79%	84%	76%	69%	82%	67%	77%	76%	74%	79%	85%	81%	66%
58.5%	62%	66%	67%	60%	53%	52%	67%	70%	60%	61%	51%	61%	52%	51%	55%	60%	64%	54%	50%	50%	63%
67.7%	70%	73%	77%	77%	81%	53%	66%	72%	69%	78%	60%	65%	71%	66%	60%	77%	63%	67%	53%	76%	47%
76.7%	80%	90%	86%	78%	94%	70%	76%	57%	83%	77%	75%	69%	69%	75%	75%	92%	80%	70%	76%	60%	79%
61.9%	71%	70%	64%	64%	68%	42%	57%	74%	60%	58%	56%	60%	64%	57%	65%	65%	74%	68%	64%	64%	35%
74.4%	87%	62%	88%	77%	34%	55%	80%	90%	88%	88%	68%	47%	88%	74%	79%	84%	86%	77%	55%	79%	77%
69.4%	79%	77%	76%	76%	83%	59%	79%	66%	57%	78%	62%	57%	69%	62%	79%	79%	60%	56%	71%	59%	73%
72.5%	72%	73%	79%	82%	79%	73%	74%	58%	72%	85%	76%	65%	83%	78%	63%	64%	66%	72%	72%	69%	68%
82.9%	80%	87%	78%	80%	84%	84%	86%	83%	82%	81%	84%	72%	91%	93%	90%	89%	84%	70%	87%	81%	75%
76.7%	78%	82%	80%	79%	85%	82%	75%	75%	84%	79%	80%	71%	63%	64%	76%	76%	72%	74%	80%	74%	81%
64.7%	76%	74%	75%	79%	68%	81%	57%	60%	55%	69%	77%	43%	57%	60%	67%	62%	57%	58%	69%	57%	57%
78.8%	76%	86%	84%	82%	89%	75%	81%	78%	85%	84%	84%	59%	76%	62%	75%	77%	83%	88%	79%	81%	71%
58.9%	59%	73%	61%	66%	66%	61%	48%	54%	56%	72%	55%	45%	59%	68%	56%	52%	47%	61%	63%	63%	51%
66.9%	70%	72%	71%	71%	68%	54%	64%	74%	68%	72%	57%	66%	72%	68%	74%	78%	69%	46%	69%	74%	47%
63.8%	73%	69%	66%	66%	84%	38%	63%	70%	76%	62%	74%	53%	66%	50%	77%	66%	61%	31%	52%	68%	74%
76.3%	91%	84%	85%	85%	77%	73%	76%	76%	75%	76%	70%	70%	72%	70%	75%	80%	69%	74%	70%		77%
72.5%	83%	78%	79%	90%	84%	54%	69%	83%	81%	67%	82%	79%	72%	56%	83%	78%	62%	63%	71%	54%	55%
76.6%	81%	82%	86%	81%	81%	71%	79%	78%	73%	86%	78%	70%	82%	71%	83%	81%	73%	59%	71%	69%	74%
73.7%	69%	75%	69%	82%	82%	69%	72%	73%	82%	67%	65%	59%	73%	69%	79%	71%	75%	78%	78%	79%	82%
67.2%	67%	66%	72%	59%	59%	72%	69%	68%	59%	74%	76%	82%	67%	72%	59%	70%	66%	63%	63%	69%	59%
71.4%	85%	60%	79%	90%	77%	58%	66%	73%	70%	71%	67%	57%	68%	67%	79%	82%	87%	70%	56%	57%	81%
80.6%	84%	87%	81%	88%	63%	93%	78%	78%	78%	79%	82%	92%	79%	74%	89%	74%	76%	82%	84%	77%	74%
60.2%	65%	63%	68%	62%	49%	69%	65%	59%	56%	59%	59%	60%	66%	60%	54%	58%	59%	55%	64%	55%	59%
80.0%	85%	81%	90%	91%	84%	77%	78%	70%	80%	88%	78%	81%	86%	84%	80%	82%	72%	70%	77%	73%	74%
85.0%	90%	91%	90%	90%	85%	91%	80%	91%	90%	86%	94%	75%	90%	91%	93%	97%	72%	70%	94%	90%	35%
71.2%	80%	74%	78%	83%	75%	66%	75%	63%	70%	82%	68%	69%	73%	68%	80%	73%	71%	48%	70%	66%	63%
92.3%	94%	100%	94%	93%	93%	94%	97%	98%	93%	91%	90%	83%	99%	94%	99%	100%	99%	97%	96%	59%	76%
78.7%	80%	82%	82%	82%	60%	73%	78%	86%	74%	87%	83%	79%	84%	73%	86%	76%	81%	77%	82%	69%	79%
58.9%	63%	62%	59%	59%	63%	52%	62%	54%	50%	61%	57%	62%	54%	62%	66%	63%	63%	59%	61%	52%	52%
81.4%	79%	90%	81%	77%	72%	81%	80%	67%	76%	73%	97%	95%	76%	90%	80%	85%	79%	96%	87%	83%	66%

Model Similarity Dendrogram

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