	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 4.1 Fast
Score	1st 73.2%	6th 70.4%	2nd 73.0%	7th 70.0%	17th 65.6%	19th 64.6%	12th 68.6%	10th 69.0%	14th 67.5%	8th 69.7%	9th 69.3%	20th 64.3%	11th 68.9%	13th 67.6%	5th 70.6%	4th 71.2%	18th 64.9%	21st 61.4%	16th 66.5%	15th 67.0%	3rd 71.2%
60.3%	69%	64%	66%	67%	62%	55%	53%	64%	57%	55%	56%	64%	61%	61%	59%	64%	48%	57%	59%	64%	62%
63.6%	64%	64%	63%	63%	29%	76%	63%	61%	54%	55%	76%	82%	76%	77%	55%	59%	55%	67%	77%	68%	52%
92.2%	100%	98%	100%	100%	78%	92%	92%	91%	86%	91%	95%	85%	92%	95%	96%	100%	94%	100%	89%	81%	81%
76.9%	76%	70%	80%	70%	76%	70%	70%	89%	70%	76%	89%	70%	76%	70%	89%	89%	73%	89%	70%	76%	76%
66.9%	72%	59%	80%	89%	50%	66%	80%	65%	69%	61%	61%	61%	61%	61%	72%	72%	52%	47%	69%	58%	100%
68.3%	69%	71%	69%	69%	76%	62%	70%	77%	70%	70%	70%	62%	70%	63%	69%	73%	66%	62%	62%	56%	79%
77.7%	84%	87%	79%	77%	70%	80%	83%	90%	100%	70%	75%	75%	75%	87%	77%	89%	54%	42%	76%	87%	75%
57.7%	66%	66%	66%	63%	63%	45%	61%	62%	49%	79%	58%	54%	58%	56%	56%	49%	62%	46%	41%	50%	62%
71.7%	69%	69%	77%	69%	77%	58%	61%	68%	61%	69%	78%	69%	77%	68%	68%	73%	77%	76%	73%	84%	84%
66.3%	72%	66%	63%	67%	76%	53%	72%	63%	63%	72%	72%	76%	63%	53%	72%	66%	61%	60%	67%	63%	72%
60.8%	67%	60%	60%	60%	44%	72%	60%	75%	60%	49%	60%	57%	49%	60%	41%	66%	40%	41%	89%	67%	100%
72.7%	73%	73%	73%	73%	72%	73%	68%	73%	89%	72%	68%	65%	68%	80%	72%	80%	68%	55%	75%	77%	80%
57.1%	52%	62%	66%	54%	61%	63%	56%	49%	58%	48%	69%	42%	67%	60%	69%	55%	67%	54%	69%	37%	41%
67.3%	75%	75%	75%	63%	50%	70%	75%	63%	69%	53%	77%	69%	69%	71%	69%	65%	66%	70%	83%	53%	53%
78.0%	84%	83%	84%	63%	77%	96%	71%	58%	66%	92%	100%	53%	76%	80%	84%	80%	81%	72%	74%	73%	92%
60.0%	62%	61%	70%	62%	54%	56%	62%	66%	55%	62%	62%	62%	61%	65%	63%	59%	57%	42%	53%	60%	67%
58.3%	68%	72%	68%	72%	72%	43%	56%	45%	51%	58%	58%	43%	56%	55%	68%	71%	37%	41%	56%	67%	67%
74.9%	82%	74%	74%	82%	62%	44%	68%	84%	72%	92%	61%	69%	74%	68%	100%	88%	80%	70%	59%	77%	92%
58.5%	69%	57%	59%	57%	76%	35%	59%	60%	59%	57%	59%	34%	57%	39%	100%	85%	57%	45%	42%	72%	50%
84.0%	82%	73%	87%	91%	100%	80%	82%	87%	88%	87%	77%	88%	88%	95%	89%	95%	68%	75%	86%	70%	76%
59.6%	58%	64%	70%	58%	56%	60%	70%	47%	64%	64%	62%	59%	70%	68%	47%	49%	64%	53%	61%	61%	47%
57.5%	63%	51%	52%	63%	61%	42%	59%	64%	62%	62%	52%	63%	52%	57%	63%	68%	52%	63%	42%	51%	65%
60.3%	55%	61%	55%	63%	53%	66%	58%	57%	66%	58%	58%	53%	66%	66%	69%	58%	66%	60%	55%	64%	60%
54.2%	56%	61%	56%	45%	52%	64%	43%	48%	54%	58%	56%	45%	52%	59%	50%	47%	64%	65%	64%	45%	54%
70.9%	74%	89%	74%	61%	69%	80%	78%	68%	69%	58%	80%	80%	80%	70%	68%	65%	60%	70%	78%	59%	58%
50.0%	54%	49%	56%	53%	46%	46%	49%	51%	47%	55%	52%	47%	51%	55%	48%	56%	56%	39%	52%	51%	38%
67.9%	80%	71%	79%	81%	86%	41%	56%	78%	70%	75%	44%	70%	71%	49%	72%	74%	64%	48%	60%	78%	78%
59.8%	66%	69%	69%	64%	41%	58%	65%	61%	49%	67%	61%	62%	62%	59%	57%	60%	54%	43%	50%	62%	77%
81.0%	92%	92%	92%	83%	83%	75%	80%	75%	76%	75%	85%	79%	65%	78%	80%	89%	65%	72%	88%	77%	100%
66.8%	79%	59%	79%	77%	61%	55%	77%	76%	71%	75%	59%	58%	76%	60%	64%	70%	81%	23%	58%	72%	72%
71.0%	80%	71%	81%	79%	80%	61%	76%	68%	75%	77%	66%	69%	68%	72%	72%	69%	66%	60%	63%	62%	76%
59.8%	57%	59%	57%	57%	78%	64%	64%	49%	70%	49%	61%	71%	64%	61%	57%	58%	57%	57%	67%	60%	39%
77.6%	81%	78%	81%	81%	59%	73%	73%	89%	67%	89%	76%	66%	73%	76%	81%	79%	81%	76%	70%	100%	81%
66.4%	68%	68%	71%	61%	63%	60%	69%	65%	67%	73%	68%	56%	56%	64%	72%	73%	76%	68%	63%	70%	64%
61.3%	77%	53%	69%	58%	44%	64%	69%	83%	69%	69%	54%	56%	69%	40%	70%	73%	52%	51%	37%	72%	58%
58.2%	54%	66%	66%	60%	35%	63%	59%	59%	61%	63%	69%	60%	61%	60%	54%	47%	52%	58%	55%	66%	54%
71.9%	88%	84%	74%	63%	82%	83%	68%	56%	67%	72%	79%	56%	72%	72%	64%	68%	80%	67%	75%	50%	90%
77.9%	100%	80%	85%	78%	78%	89%	86%	91%	85%	89%	71%	64%	85%	67%	76%	83%	54%	50%	83%	56%	86%
66.2%	77%	68%	73%	69%	67%	61%	67%	67%	65%	69%	59%	69%	74%	68%	62%	68%	61%	61%	67%	66%	52%
93.9%	100%	98%	100%	100%	78%	92%	92%	91%	86%	91%	95%	85%	92%	95%	100%	98%	94%	95%	89%	100%	100%
78.6%	74%	69%	81%	84%	70%	73%	83%	80%	78%	84%	84%	80%	77%	81%	78%	80%	77%	81%	71%	76%	90%
81.4%	81%	85%	81%	83%	88%	56%	79%	92%	73%	89%	92%	61%	81%	94%	83%	81%	82%	92%	81%	72%	83%
71.7%	77%	78%	79%	79%	66%	62%	67%	62%	67%	70%	76%	74%	70%	71%	79%	70%	71%	76%	63%	70%	79%

Model Similarity Dendrogram

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