	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	5th 71.0%	1st 72.7%	2nd 72.6%	4th 71.3%	19th 64.0%	11th 69.1%	13th 68.7%	14th 68.3%	9th 69.6%	7th 70.3%	8th 70.1%	16th 67.0%	6th 70.4%	15th 68.2%	12th 68.9%	3rd 71.4%	17th 66.7%	20th 62.7%	10th 69.3%	18th 65.4%	21st 61.6%
76.9%	81%	79%	78%	81%	62%	70%	73%	81%	79%	79%	82%	87%	79%	74%	64%	83%	79%	75%	82%	88%	59%
68.4%	67%	70%	67%	67%	38%	68%	69%	66%	73%	63%	68%	68%	75%	68%	75%	70%	71%	70%	74%	77%	73%
66.3%	69%	66%	75%	59%	59%	72%	62%	69%	59%	75%	69%	69%	69%	69%	62%	70%	58%	52%	56%	91%	62%
85.7%	89%	85%	89%	93%	74%	85%	89%	86%	89%	100%	80%	80%	93%	77%	85%	100%	80%	81%	80%	78%
84.1%	81%	88%	75%	81%	83%	74%	75%	87%	90%	87%	90%	81%	90%	81%	89%	95%	90%	97%	72%		75%
63.7%	62%	66%	62%	62%	74%	70%	57%	80%	64%	63%	71%	58%	64%	57%	62%	58%	61%	62%	57%	57%	70%
76.1%	78%	75%	78%	78%	78%	81%	74%	78%	78%	76%	78%	69%	74%	82%	78%	78%	66%	67%	68%	90%	74%
70.0%	70%	71%	71%	77%	71%	61%	66%	77%	70%	64%	71%	71%	71%	77%	69%	73%	72%	66%	71%	71%	60%
84.3%	82%	84%	78%	81%	81%	62%	74%	95%	74%	95%	95%	78%	95%	78%	89%	94%	95%	93%	81%	90%	76%
74.4%	80%	71%	64%	71%	80%	80%	69%	59%	80%	68%	80%	80%	80%	80%	69%	71%	71%	80%	80%	80%	69%
69.3%	74%	82%	82%	74%	68%	86%	82%	68%	68%	68%	74%	74%	60%	74%	60%	66%	52%	51%	72%	68%	52%
66.0%	65%	60%	73%	65%	58%	65%	74%	71%	73%	63%	71%	55%	74%	55%	68%	66%	73%	64%	65%	73%	56%
55.0%	48%	66%	71%	68%	41%	77%	57%	41%	57%	53%	68%	46%	58%	71%	48%	52%	41%	41%	69%	41%	41%
63.0%	64%	70%	67%	71%	69%	60%	64%	56%	62%	62%	62%	59%	66%	59%	67%	71%	59%	56%	62%	49%	69%
74.1%	82%	81%	74%	74%	74%	73%	74%	66%	66%	74%	75%	66%	77%	87%	75%	82%	77%	60%	78%	66%	76%
63.0%	75%	71%	78%	78%	48%	56%	61%	65%	64%	64%	45%	69%	71%	56%	65%	73%	66%	62%	61%	47%	47%
57.7%	68%	82%	68%	62%	63%	54%	63%	42%	63%	52%	54%	43%	57%	57%	62%	66%	48%	56%	54%	48%	50%
69.6%	80%	80%	74%	87%	74%	43%	60%	80%	72%	72%	62%	69%	72%	51%	74%	74%	75%	70%	62%	72%	58%
49.8%	51%	40%	50%	48%	49%	36%	57%	58%	62%	57%	51%	39%	57%	47%	64%	57%	47%	41%	30%	58%	47%
86.6%	84%	87%	93%	84%	87%	83%	90%	88%	89%	93%	89%	76%	91%	89%	78%	88%	93%	83%	86%	76%	91%
66.6%	66%	65%	69%	65%	66%	72%	70%	62%	70%	65%	69%	70%	70%	69%	64%	62%	70%	60%	73%	70%	51%
73.3%	73%	82%	87%	77%	70%	70%	75%	73%	71%	71%	70%	78%	75%	77%	74%	75%	73%	66%	78%	73%	52%
75.5%	71%	78%	78%	68%	79%	78%	79%	82%	78%	79%	68%	76%	79%	88%	73%	78%	79%	49%	91%	63%	72%
61.4%	61%	74%	68%	68%	55%	75%	56%	56%	64%	61%	65%	54%	68%	65%	52%	61%	55%	47%	75%	55%	55%
68.2%	66%	76%	78%	76%	69%	66%	69%	59%	69%	71%	71%	69%	65%	65%	69%	64%	75%	61%	69%	71%	54%
58.9%	51%	63%	55%	52%	57%	74%	60%	50%	63%	63%	67%	60%	63%	80%	54%	55%	55%	45%	67%	63%	40%
63.0%	59%	57%	59%	56%	50%	81%	64%	57%	61%	64%	83%	71%	65%	78%	59%	59%	50%	69%	69%	52%	59%
59.9%	64%	63%	64%	64%	87%	42%	64%	63%	68%	64%	64%	50%	50%	37%	71%	64%	64%	58%	50%	57%	49%
64.4%	71%	77%	77%	80%	70%	60%	71%	64%	65%	56%	58%	80%	56%	56%	64%	66%	58%	49%	61%	49%	64%
62.4%	74%	70%	69%	69%	62%	60%	47%	70%	71%	62%	62%	61%	62%	44%	72%	70%	57%	67%	74%	40%	48%
64.0%	60%	69%	65%	60%	60%	70%	63%	59%	63%	68%	71%	60%	65%	68%	62%	63%	63%	57%	75%	63%	59%
63.0%	54%	63%	54%	69%	69%	57%	66%	60%	69%	54%	60%	60%	60%	60%	66%	59%	71%	78%	73%	60%	60%
75.5%	79%	77%	86%	69%	69%	82%	73%	79%	69%	86%	79%	79%	79%	79%	73%	80%	68%	61%	73%	73%	73%
75.8%	78%	73%	80%	78%	62%	78%	72%	77%	78%	78%	74%	76%	75%	76%	74%	75%	80%	76%	76%	76%	80%
57.3%	65%	78%	73%	71%	30%	63%	48%	48%	48%	51%	48%	52%	51%	52%	65%	72%	63%	50%	72%	51%	52%
55.4%	61%	61%	61%	61%	24%	68%	61%	66%	56%	55%	64%	62%	61%	58%	52%	48%	35%	55%	62%	51%	42%
70.4%	74%	81%	69%	69%	55%	79%	72%	56%	72%	72%	69%	69%	72%	82%	72%	74%	75%	62%	74%	72%	59%
75.6%	79%	65%	81%	75%	75%	82%	87%	87%	87%	87%	75%	62%	75%	69%	81%	75%	62%	55%	75%	72%	81%
59.0%	71%	62%	59%	59%	26%	56%	64%	62%	62%	68%	59%	62%	62%	45%	67%	62%	64%	62%	49%	69%	48%
75.5%	86%	77%	86%	69%	69%	82%	73%	79%	69%	86%	79%	79%	79%	79%	73%	80%	68%	61%	66%	73%	73%
72.1%	78%	78%	83%	89%	54%	69%	89%	80%	69%	95%	77%	58%	77%	58%	80%	80%	75%	43%	67%	39%	77%
75.3%	85%	80%	73%	80%	76%	74%	73%	74%	73%	80%	71%	76%	73%	85%	71%	76%	73%	67%	73%	73%	76%
72.9%	79%	83%	79%	79%	85%	79%	68%	62%	65%	60%	78%	79%	72%	72%	72%	87%	60%	73%	79%	62%	58%

Model Similarity Dendrogram

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