	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	3rd 73.1%	2nd 73.1%	1st 73.3%	4th 72.5%	18th 65.4%	14th 67.3%	9th 70.4%	12th 69.9%	13th 68.2%	8th 70.9%	7th 71.0%	15th 65.9%	5th 71.3%	17th 65.5%	10th 70.2%	11th 70.0%	16th 65.8%	20th 63.6%	6th 71.2%	19th 64.1%	21st 61.4%
65.7%	74%	64%	71%	79%	67%	57%	64%	70%	63%	78%	64%	43%	71%	67%	72%	69%	68%	59%	72%	64%	43%
70.0%	84%	69%	77%	77%	47%	79%	76%	77%	69%	67%	84%	76%	78%	76%	60%	60%	69%	60%	68%	67%	49%
77.3%	92%	75%	84%	84%	68%	81%	78%	78%	68%	84%	92%	92%	92%	78%	78%	78%	76%	72%	81%	46%	46%
71.4%	80%	60%	64%	62%	60%	77%	75%	84%	63%	77%	61%	61%	77%	80%	80%	77%	80%	60%	64%	77%	80%
73.2%	86%	80%	86%	80%	78%	93%	86%	70%	70%	80%	73%	80%	65%	73%	67%	80%	55%	61%	86%	55%	34%
78.8%	74%	79%	74%	74%	88%	88%	73%	100%	81%	78%	88%	83%	74%	88%	74%	74%	80%	75%	78%	73%	58%
75.0%	78%	78%	77%	81%	78%	76%	84%	81%	72%	78%	78%	62%	79%	62%	67%	78%	76%	74%	79%	62%	76%
62.1%	70%	70%	64%	64%	40%	51%	71%	66%	63%	56%	61%	61%	61%	51%	72%	66%	60%	68%	61%	61%	68%
84.4%	85%	96%	91%	91%	86%	66%	85%	92%	86%	83%	92%	91%	92%	91%	80%	78%	93%	73%	85%	92%	44%
63.2%	61%	81%	69%	71%	61%	61%	55%	62%	61%	69%	61%	61%	61%	61%	69%	67%	52%	51%	61%	61%	71%
70.8%	77%	83%	80%	77%	80%	79%	80%	65%	67%	62%	80%	77%	61%	62%	72%	72%	44%	50%	91%	74%	53%
68.1%	64%	74%	71%	66%	80%	71%	71%	69%	66%	68%	71%	72%	68%	71%	80%	69%	49%	40%	72%		69%
70.5%	69%	71%	71%	64%	68%	85%	64%	61%	68%	64%	80%	68%	71%	75%	71%	73%	68%	68%	85%	68%	68%
77.1%	86%	89%	89%	83%	72%	77%	70%	81%	81%	83%	81%	52%	84%	52%	81%	84%	69%	78%	81%	57%	89%
72.4%	73%	82%	76%	75%	76%	70%	76%	73%	73%	66%	76%	73%	71%	65%	73%	75%	65%	70%	69%	69%	75%
73.7%	80%	74%	90%	80%	71%	55%	68%	78%	71%	85%	74%	55%	88%	63%	73%	76%	66%	74%	71%		81%
56.4%	65%	68%	69%	65%	57%	50%	65%	50%	61%	54%	61%	50%	54%	61%	61%	67%	57%	25%	69%	42%	33%
58.3%	73%	57%	65%	77%	73%	30%	42%	63%	51%	61%	42%	73%	64%	31%	68%	55%	61%	66%	57%	49%	66%
64.1%	70%	58%	70%	58%	47%	52%	70%	77%	60%	76%	77%	44%	61%	70%	78%	67%	77%	60%	48%	58%	68%
71.8%	77%	78%	77%	61%	77%	66%	77%	79%	71%	77%	58%	58%	77%	58%	76%	77%	74%	71%	86%	58%	74%
54.6%	52%	57%	63%	57%	24%	64%	63%	49%	60%	63%	63%	63%	59%	61%	53%	52%	45%	38%	51%	63%	47%
73.0%	74%	83%	83%	78%	54%	74%	77%	72%	72%	68%	90%	72%	77%	80%	65%	77%	64%	66%	75%	71%	60%
71.3%	67%	78%	67%	67%	74%	70%	73%	84%	78%	84%	78%	73%	86%	73%	59%	76%	71%	60%	65%	55%	60%
77.3%	75%	86%	82%	82%	78%	78%	75%	71%	73%	79%	78%	72%	73%	83%	77%	91%	73%	68%	84%	73%	73%
78.7%	76%	84%	68%	85%	78%	84%	88%	82%	84%	82%	71%	61%	84%	61%	83%	83%	76%	72%	84%	84%	83%
56.1%	52%	63%	60%	52%	55%	57%	62%	56%	54%	62%	58%	58%	55%	61%	53%	54%	45%	52%	63%	72%	35%
73.7%	78%	76%	80%	86%	88%	58%	73%	75%	72%	79%	61%	54%	79%	63%	91%	74%	75%	75%	81%	72%	57%
63.4%	71%	70%	68%	71%	77%	47%	63%	68%	66%	64%	68%	53%	68%	38%	77%	71%	74%	63%	53%	48%	53%
69.1%	69%	80%	80%	79%	93%	61%	78%	63%	63%	64%	69%	72%	55%	64%	69%	69%	60%	60%	74%	64%	66%
63.6%	74%	74%	74%	74%	66%	41%	55%	74%	74%	61%	61%	63%	69%	41%	68%	61%	79%	72%	67%	52%	35%
80.0%	91%	85%	78%	78%	66%	79%	85%	73%	85%	79%	91%	85%	91%	74%	70%	78%	85%	85%	71%	83%	69%
78.3%	67%	83%	74%	74%	90%	77%	80%	80%	90%	74%	67%	67%	67%	80%	80%	80%	82%	86%	77%	90%	80%
53.4%	64%	50%	58%	58%	44%	55%	52%	52%	44%	58%	64%	64%	64%	52%	52%	52%	47%	48%	55%	24%	64%
64.2%	73%	61%	65%	73%	59%	60%	63%	67%	68%	73%	62%	58%	61%	55%	74%	67%	68%	58%	58%	58%	68%
61.8%	68%	72%	68%	78%	24%	67%	44%	68%	47%	49%	49%	68%	68%	68%	60%	50%	47%	63%	76%	84%	79%
53.1%	50%	54%	62%	54%	34%	59%	55%	37%	44%	54%	54%	61%	62%	65%	50%	51%	58%	45%	61%	52%	54%
57.0%	60%	61%	58%	58%	46%	64%	54%	48%	61%	64%	60%	60%	60%	56%	52%	58%	50%	53%	63%	61%	50%
69.9%	84%	69%	77%	77%	81%	90%	84%	77%	84%	77%	64%	57%	84%	58%	70%	70%	52%	52%	70%	74%	17%
82.7%	83%	82%	88%	83%	69%	77%	90%	83%	90%	77%	100%	64%	83%	69%	80%	85%	86%	95%	77%	86%	89%
78.3%	92%	75%	84%	84%	68%	81%	78%	78%	68%	84%	92%	92%	92%	78%	78%	78%	76%	72%	81%	46%	68%
75.2%	78%	76%	78%	78%	61%	73%	79%	74%	73%	91%	78%	55%	78%	66%	87%	75%	72%	66%	91%	71%	80%
55.7%	62%	60%	51%	53%	51%	47%	66%	53%	55%	62%	53%	66%	51%	66%	56%	53%	55%	55%	53%	51%	50%
63.1%	65%	80%	69%	69%	57%	69%	61%	46%	61%	55%	69%	65%	53%	69%	61%	61%	49%	76%	69%	61%	60%

Model Similarity Dendrogram

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