	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 68.3%	7th 67.0%	3rd 68.7%	2nd 69.0%	8th 67.0%	18th 62.5%	9th 66.6%	6th 67.5%	10th 66.2%	12th 65.8%	13th 65.4%	21st 61.0%	15th 64.6%	20th 62.2%	5th 67.5%	1st 69.5%	14th 65.2%	19th 62.4%	16th 64.0%	17th 63.6%	11th 66.0%
78.9%	78%	77%	100%	100%	60%	67%	76%	77%	90%	75%	90%	39%	78%	73%	89%	77%	75%	79%	88%	91%	78%
65.0%	70%	60%	70%	73%	37%	73%	66%	70%	60%	79%	70%	64%	70%	67%	65%	67%	52%	57%	56%		73%
46.0%	44%	41%	54%	44%	44%	41%	44%	47%	44%	47%	54%	54%	47%	54%	44%	47%	43%	41%	41%	47%	44%
65.5%	71%	57%	71%	71%	77%	46%	71%	71%	65%	79%	62%	70%	71%	39%	68%	77%	63%	67%	56%	65%	59%
73.1%	81%	70%	76%	76%	80%	71%	76%	80%	72%	76%	64%	64%	70%	70%	70%	70%	73%	66%	80%	80%	70%
85.1%	81%	82%	82%	82%	68%	82%	87%	68%	87%	87%	87%	88%	87%	87%	93%	91%	91%	87%	91%	92%	87%
64.4%	64%	60%	60%	64%	82%	60%	62%	62%	79%	57%	72%	68%	57%	65%	53%	77%	82%	57%	66%	53%	53%
72.9%	78%	82%	59%	59%	75%	62%	82%	78%	82%	64%	65%	82%	75%	59%	78%	77%	81%	77%	74%	54%	88%
83.0%	79%	82%	82%	82%	76%	69%	82%	89%	89%	91%	82%	79%	89%	79%	91%	89%	91%	75%	82%	83%	83%
71.3%	82%	70%	74%	80%	70%	70%	66%	74%	74%	70%	70%	70%	84%	70%	57%	61%	62%	79%	70%	87%	58%
43.1%	48%	46%	54%	54%	23%	54%	48%	60%	47%	39%	31%	54%	31%	39%	32%	46%	42%	17%	54%	54%	32%
71.5%	75%	75%	70%	76%	71%	70%	71%	76%	74%	61%	74%	70%	57%	74%	78%	74%	72%	69%	70%	71%	74%
76.6%	81%	76%	87%	75%	91%	81%	87%	61%	75%	87%	75%	76%	68%	100%	68%	86%	61%	63%	88%	61%	61%
72.0%	66%	74%	74%	66%	89%	69%	68%	89%	66%	70%	89%	56%	74%	66%	75%	89%	76%	58%	66%	58%	74%
79.5%	89%	89%	81%	81%	71%	77%	78%	74%	89%	89%	84%	89%	89%	79%	73%	83%	77%	69%	74%	71%	64%
68.8%	66%	68%	73%	75%	60%	56%	68%	75%	66%	65%	76%	42%	68%	76%	75%	70%	72%	59%	68%	66%	100%
60.5%	69%	76%	76%	58%	91%	56%	63%	50%	58%	50%	69%	50%	48%	60%	50%	58%	48%	60%	65%	64%	52%
54.8%	60%	54%	61%	61%	75%	35%	52%	64%	61%	46%	54%	74%	54%	38%	56%	55%	46%	46%	45%	56%	58%
39.0%	43%	20%	43%	37%	78%	22%	31%	37%	43%	50%	31%	22%	43%	22%	61%	61%	40%	20%	22%	39%	54%
54.5%	65%	67%	60%	60%	56%	52%	67%	51%	47%	56%	56%	39%	56%	39%	55%	60%	51%	41%	64%	39%	64%
60.5%	62%	66%	57%	54%	58%	62%	60%	60%	55%	63%	66%	66%	66%	60%	50%	59%	60%	60%	67%	68%	52%
73.5%	73%	73%	73%	73%	62%	88%	71%	62%	66%	82%	88%	82%	76%	78%	76%	82%	82%	74%	85%	54%	44%
58.7%	53%	62%	56%	64%	60%	65%	58%	63%	54%	62%	53%	48%	60%	65%	58%	56%	60%	53%	65%	54%	64%
74.5%	82%	75%	82%	82%	63%	78%	75%	75%	75%	75%	75%	60%	82%	74%	77%	74%	78%	68%	63%	63%	88%
70.2%	73%	68%	64%	68%	75%	65%	64%	88%	52%	62%	70%	67%	62%	68%	80%	83%	80%	65%	73%	72%	75%
63.6%	56%	66%	63%	60%	68%	89%	66%	46%	58%	66%	75%	74%	56%	74%	56%	60%	61%	61%	66%	52%	63%
59.7%	61%	59%	68%	68%	59%	48%	46%	71%	65%	61%	54%	47%	59%	54%	63%	59%	54%	65%	59%	54%	79%
44.6%	60%	41%	47%	60%	66%	19%	40%	52%	50%	47%	34%	27%	34%	27%	54%	57%	50%	50%	19%	41%	61%
73.9%	83%	100%	88%	100%	74%	63%	83%	74%	83%	61%	55%	63%	63%	66%	63%	78%	63%	61%	84%	70%	76%
73.1%	73%	70%	73%	82%	77%	78%	77%	74%	70%	71%	68%	65%	74%	63%	66%	73%	88%	79%	70%	74%	71%
50.4%	50%	50%	50%	45%	50%	48%	49%	51%	56%	43%	55%	48%	49%	54%	51%	56%	44%	54%	56%	56%	43%
86.4%	88%	92%	77%	88%	88%	92%	88%	85%	88%	85%	77%	77%	85%	77%	88%	85%	90%	93%	92%	88%	92%
46.0%	44%	41%	54%	44%	44%	41%	44%	47%	44%	47%	54%	54%	47%	54%	44%	47%	43%	47%	41%	41%	44%
56.3%	68%	49%	80%	87%	54%	38%	51%	56%	56%	68%	39%	39%	51%	46%	83%	70%	51%	62%	37%	39%	59%
57.5%	65%	65%	65%	65%	41%	68%	51%	70%	54%	62%	48%	63%	62%	47%	54%	58%	54%	62%	41%	54%	58%
60.5%	62%	61%	63%	70%	55%	49%	67%	61%	59%	68%	59%	53%	61%	53%	70%	61%	57%	53%	47%	78%	63%
72.0%	71%	76%	76%	79%	87%	62%	86%	87%	76%	64%	73%	57%	62%	57%	76%	73%	68%	65%	57%	87%	73%
62.0%	69%	65%	65%	65%	57%	73%	65%	65%	57%	69%	65%	54%	65%	60%	75%	75%	61%	57%	60%	45%	36%
53.5%	61%	53%	50%	50%	61%	50%	57%	61%	61%	47%	53%	50%	53%	50%	59%	56%	59%	36%	50%	57%	50%
93.8%	96%	100%	85%	96%	96%	100%	96%	92%	96%	92%	85%	85%	92%	85%	96%	92%	97%	100%	100%	92%	96%
63.2%	60%	68%	60%	60%	63%	55%	67%	66%	61%	60%	61%	42%	60%	51%	74%	70%	69%	83%	49%		85%
81.3%	83%	88%	83%	83%	82%	81%	90%	84%	84%	83%	75%	84%	83%	76%	91%	83%	69%	73%	81%	72%	80%
64.8%	52%	68%	69%	52%	67%	64%	69%	58%	58%	52%	75%	68%	58%	78%	67%	66%	69%	77%	68%	67%	58%

Model Similarity Dendrogram

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