	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	5th 71.2%	2nd 72.3%	1st 72.7%	3rd 71.7%	16th 65.3%	15th 65.4%	7th 70.2%	8th 69.2%	11th 68.0%	14th 66.1%	4th 71.2%	17th 65.3%	6th 70.2%	12th 68.0%	13th 67.5%	10th 68.7%	18th 63.4%	19th 61.8%	9th 69.1%	20th 61.0%	21st 59.4%
66.3%	72%	71%	74%	74%	72%	57%	68%	66%	69%	68%	58%	58%	68%	67%	72%	62%	62%	62%	66%	69%	58%
69.1%	68%	75%	68%	77%	47%	77%	75%	62%	56%	67%	78%	78%	78%	76%	76%	65%	66%	69%	78%	60%	55%
84.2%	92%	78%	84%	92%	68%	81%	78%	100%	78%	92%	92%	92%	92%	78%	84%	84%	78%		92%	71%	78%
67.4%	80%	62%	80%	64%	72%	64%	75%	61%	75%	77%	61%	61%	63%	61%	76%	80%	59%	60%	59%	62%	63%
74.0%	86%	67%	89%	89%	70%	87%	86%	78%	74%	60%	67%	80%	59%	73%	73%	73%	66%	57%	86%	55%	80%
79.9%	74%	79%	74%	84%	84%	83%	81%	100%	78%	78%	88%	78%	88%	88%	74%	74%	71%	84%	78%	73%	66%
61.7%	61%	75%	69%	65%	52%	50%	76%	78%	71%	54%	76%	68%	53%	65%	38%	62%	72%	68%	70%	36%	36%
65.5%	70%	71%	64%	65%	68%	59%	71%	78%	63%	71%	68%	63%	71%	55%	64%	69%	50%		59%	61%	71%
80.8%	78%	96%	87%	93%	92%	66%	76%	92%	85%	83%	93%	66%	92%	91%	68%	80%	68%	70%	85%	92%	44%
57.9%	67%	67%	62%	67%	61%	68%	55%	51%	54%	55%	61%	61%	55%	67%	57%	51%	49%	42%	61%	48%	57%
74.2%	86%	84%	78%	78%	74%	79%	74%	69%	78%	55%	80%	62%	61%	80%	75%	55%	83%	62%	91%	74%	81%
66.7%	64%	71%	71%	64%	71%	71%	71%	72%	64%	66%	78%	72%	71%	70%	71%	64%	49%	48%	60%	69%	64%
64.1%	56%	71%	64%	64%	74%	64%	60%	61%	62%	54%	71%	64%	80%	75%	52%	59%	68%		79%	79%	24%
56.8%	68%	69%	70%	70%	41%	60%	68%	63%	68%	42%	68%	40%	48%	68%	46%	51%	49%	57%	74%	38%	34%
72.6%	76%	73%	76%	75%	76%	76%	73%	67%	73%	71%	76%	77%	76%	73%	73%	75%	62%	62%	76%	64%	75%
69.9%	77%	78%	90%	64%	64%	47%	71%	74%	68%	79%	65%	64%	80%	75%	74%	68%	71%	70%	65%	77%	47%
59.1%	71%	68%	80%	69%	57%	52%	64%	53%	57%	37%	69%	42%	50%	65%	78%	64%	65%	33%	50%	57%	60%
55.3%	66%	53%	55%	73%	73%	30%	42%	60%	51%	57%	42%	43%	61%	47%	59%	69%	59%	68%	39%	46%	68%
57.6%	64%	49%	67%	64%	55%	38%	70%	61%	52%	62%	61%	44%	66%	52%	91%	67%	50%	45%	35%	58%	58%
71.9%	77%	73%	77%	68%	61%	80%	86%	74%	74%	75%	86%	74%	71%	69%	59%	82%	56%	83%	79%	44%	62%
52.8%	52%	51%	58%	42%	41%	64%	63%	51%	61%	47%	57%	60%	63%	61%	49%	52%	38%	56%	52%	54%	36%
73.5%	62%	83%	83%	74%	70%	83%	77%	59%	73%	74%	89%	67%	83%	83%	66%	72%	73%	64%	81%	72%	55%
65.4%	60%	64%	63%	67%	64%	68%	73%	78%	78%	63%	61%	55%	67%	64%	63%	73%	66%	70%	57%	64%	55%
74.0%	84%	83%	82%	82%	75%	81%	68%	67%	73%	72%	82%	63%	84%	73%	68%	78%	75%	67%	79%	76%	41%
65.1%	71%	83%	76%	73%	69%	66%	76%	70%	77%	45%	83%	68%	47%	52%	64%	56%	69%	63%	83%	42%	35%
54.4%	54%	63%	62%	53%	46%	57%	62%	53%	55%	62%	55%	59%	46%	62%	46%	59%	46%	51%	59%	58%	35%
72.7%	74%	79%	79%	82%	72%	58%	76%	81%	76%	77%	76%	75%	91%	75%	73%	80%	68%	49%	69%	62%	55%
66.0%	72%	70%	68%	71%	77%	46%	69%	70%	72%	70%	68%	58%	68%	51%	71%	74%	73%	72%	53%	35%	77%
71.1%	86%	93%	80%	80%	93%	61%	78%	60%	64%	64%	64%	72%	61%	64%	71%	74%	61%	61%	74%	69%	64%
63.5%	68%	74%	67%	68%	66%	48%	55%	90%	79%	67%	69%	34%	67%	66%	67%	77%	61%	70%	72%	35%	34%
81.5%	78%	85%	78%	82%	91%	79%	79%	74%	83%	59%	75%	82%	91%	100%	68%	82%	79%	79%	82%	85%	100%
74.8%	67%	80%	74%	67%	90%	77%	80%	59%	80%	67%	67%	67%	67%	80%	74%	74%	80%	86%	67%	87%	80%
58.8%	64%	53%	58%	64%	44%	55%	52%	71%	52%	64%	64%	64%	64%	52%	58%	58%	52%	59%	64%	64%	58%
70.7%	72%	71%	77%	76%	65%	72%	78%	79%	76%	72%	75%	51%	68%	49%	83%	79%	73%	74%	62%	49%	83%
62.2%	70%	76%	65%	73%	24%	79%	44%	79%	31%	72%	68%	69%	79%	54%	68%	58%	62%	69%	66%	49%	51%
52.3%	50%	58%	62%	54%	33%	58%	56%	33%	54%	54%	58%	62%	62%	61%	54%	54%	45%	49%	58%	44%	39%
58.0%	64%	56%	58%	58%	64%	64%	58%	47%	58%	61%	60%	55%	68%	60%	47%	55%	65%	55%	63%	61%	41%
76.7%	90%	72%	84%	84%	81%	90%	90%	77%	84%	90%	65%	84%	84%	64%	77%	76%	51%	45%	81%	52%	90%
82.0%	78%	93%	88%	88%	69%	69%	84%	78%	86%	73%	90%	91%	89%	84%	78%	86%	86%	76%	77%		77%
85.0%	92%	78%	84%	92%	68%	81%	78%	100%	78%	92%	92%	92%	92%	78%	92%	84%	78%	85%	92%	78%	78%
72.8%	78%	75%	78%	78%	61%	68%	79%	74%	73%	82%	82%	71%	79%	71%	79%	78%	69%	25%	68%	80%	80%
57.0%	61%	60%	53%	53%	62%	46%	62%	60%	55%	66%	56%	71%	61%	55%	58%	54%	52%	51%	61%	50%	51%
60.4%	61%	80%	69%	65%	53%	54%	61%	46%	58%	46%	69%	49%	55%	69%	69%	65%	53%	57%	69%	61%	60%

Model Similarity Dendrogram

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