	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 73.0%	9th 70.7%	2nd 73.3%	1st 74.0%	17th 68.1%	13th 70.1%	4th 72.2%	16th 68.5%	14th 70.0%	5th 71.8%	7th 71.1%	19th 67.3%	11th 70.6%	10th 70.7%	12th 70.5%	8th 70.9%	18th 68.0%	20th 66.4%	6th 71.5%	15th 69.4%	21st 62.9%
76.1%	73%	76%	85%	81%	72%	83%	89%	67%	81%	78%	81%	81%	77%	83%	71%	75%	63%	71%	79%	66%	66%
52.4%	55%	49%	63%	70%	9%	50%	55%	62%	48%	63%	48%	49%	42%	56%	62%	63%	56%	57%	48%	56%	40%
76.4%	82%	65%	86%	69%	69%	82%	73%	79%	69%	73%	87%	86%	79%	79%	73%	79%	73%	74%	73%	88%	66%
75.8%	73%	77%	75%	75%	69%	93%	73%	70%	75%	73%	73%	78%	75%	89%	82%	70%	77%	79%	70%	78%	67%
77.8%	84%	78%	89%	84%	79%	87%	84%	91%	80%	76%	72%	71%	76%	76%	65%	71%	76%	64%	78%	73%	79%
71.8%	58%	64%	58%	67%	65%	71%	76%	65%	80%	76%	72%	84%	76%	72%	63%	67%	84%	79%	80%	76%	74%
69.9%	67%	70%	73%	76%	67%	72%	64%	69%	70%	76%	65%	76%	63%	72%	73%	76%	68%	65%	66%	76%	64%
73.0%	89%	69%	69%	71%	83%	50%	80%	80%	77%	66%	80%	74%	69%	69%	69%	74%	66%	72%	72%	72%	83%
68.1%	65%	65%	64%	65%	58%	52%	70%	62%	70%	72%	80%	65%	65%	73%	64%	71%	77%	74%	70%	72%	76%
76.6%	84%	64%	84%	84%	78%	78%	75%	65%	78%	78%	78%	78%	78%	78%	75%	75%	77%	71%	78%	78%	75%
72.2%	83%	83%	77%	77%	83%	84%	83%	71%	71%	68%	71%	71%	65%	83%	76%	68%	54%	54%	75%	64%	55%
61.9%	78%	63%	65%	74%	69%	65%	58%	62%	63%	39%	65%	64%	48%	65%	69%	68%	36%	64%	65%	60%	60%
63.7%	61%	68%	77%	89%	64%	71%	61%	57%	55%	66%	68%	48%	62%	68%	64%	59%	61%	54%	68%		54%
69.0%	73%	68%	73%	73%	66%	64%	73%	68%	68%	66%	70%	62%	70%	62%	76%	72%	73%	63%	68%	73%	68%
81.1%	91%	84%	75%	92%	73%	80%	75%	63%	75%	92%	91%	66%	77%	89%	85%	79%	76%	82%	91%	100%	68%
64.8%	60%	65%	65%	62%	63%	66%	71%	59%	71%	63%	71%	71%	70%	66%	59%	59%	65%	51%	71%	61%	71%
68.8%	72%	83%	86%	72%	75%	59%	63%	49%	69%	59%	72%	50%	59%	69%	86%	74%	56%	67%	79%	74%	72%
55.5%	60%	62%	54%	60%	78%	28%	51%	58%	53%	45%	46%	57%	51%	46%	71%	62%	54%	62%	48%	53%	67%
39.2%	41%	28%	32%	34%	64%	25%	41%	34%	38%	58%	36%	16%	41%	28%	56%	62%	51%	29%	28%	41%	40%
75.8%	74%	74%	74%	74%	76%	72%	76%	70%	69%	84%	75%	76%	77%	75%	78%	76%	83%	76%	77%	76%	80%
67.9%	67%	78%	71%	82%	70%	88%	70%	58%	70%	74%	70%	50%	74%	82%	57%	58%	60%	57%	88%	65%	37%
76.4%	77%	84%	84%	92%	61%	84%	76%	68%	70%	84%	79%	68%	68%	92%	82%	79%	67%	60%	88%	68%	73%
75.9%	63%	72%	63%	67%	92%	90%	92%	84%	72%	84%	72%	74%	89%	78%	63%	72%	84%	60%	92%	68%	63%
52.5%	61%	65%	61%	68%	56%	55%	53%	45%	51%	55%	53%	34%	53%	56%	46%	61%	41%	41%	65%	41%	41%
62.0%	61%	65%	65%	65%	73%	61%	65%	61%	65%	61%	65%	56%	61%	55%	52%	60%	59%	68%	64%	61%	60%
50.7%	57%	57%	51%	51%	46%	44%	51%	51%	48%	67%	56%	41%	60%	54%	50%	46%	51%	51%	48%	60%	24%
72.1%	72%	82%	75%	78%	66%	69%	70%	73%	75%	88%	67%	68%	91%	61%	55%	65%	67%	71%	73%	91%	57%
81.4%	84%	84%	84%	72%	62%	79%	86%	84%	90%	79%	90%	75%	84%	79%	79%	78%	90%	83%	88%	90%	69%
77.0%	100%	79%	88%	100%	100%	63%	80%	73%	78%	64%	69%	77%	64%	64%	89%	78%	64%	60%	73%	74%	81%
66.2%	80%	60%	78%	76%	81%	57%	69%	66%	56%	60%	60%	56%	60%	48%	70%	72%	68%	68%	62%	69%	74%
69.7%	65%	71%	65%	68%	64%	76%	64%	57%	64%	77%	72%	64%	64%	78%	71%	77%	68%	81%	80%	76%	61%
50.8%	50%	63%	44%	59%	59%	47%	56%	50%	59%	56%	44%	44%	50%	50%	50%	50%	56%	56%	56%	23%	44%
75.2%	79%	65%	86%	69%	69%	82%	73%	79%	69%	73%	87%	86%	79%	79%	79%	79%	73%	74%	73%	60%	66%
81.7%	83%	85%	100%	91%	52%	80%	85%	100%	89%	91%	76%	76%	76%	76%	82%	100%	88%	81%	76%	76%	53%
75.0%	80%	58%	80%	80%	47%	81%	77%	71%	68%	85%	68%	89%	91%	77%	91%	71%	91%	82%	56%	74%	58%
69.7%	64%	74%	77%	60%	35%	85%	72%	77%	73%	68%	73%	66%	82%	85%	59%	65%	73%	65%	79%	73%	59%
83.0%	86%	86%	85%	74%	91%	85%	86%	79%	86%	76%	86%	83%	85%	82%	82%	86%	84%	84%	82%	89%	67%
57.0%	71%	56%	62%	69%	69%	67%	77%	71%	69%	69%	55%	43%	62%	45%	52%	55%	33%	51%	55%	46%	20%
84.4%	83%	100%	91%	89%	78%	91%	85%	84%	84%	91%	84%	100%	100%	77%	85%	80%	75%	76%	84%	58%	77%
86.1%	88%	74%	95%	78%	78%	91%	81%	88%	78%	81%	95%	95%	88%	88%	88%	88%	81%	82%	81%	95%	95%
71.3%	77%	75%	77%	80%	58%	71%	80%	77%	71%	71%	77%	66%	76%	66%	80%	75%	71%	37%	77%	63%	72%
68.7%	74%	70%	61%	68%	68%	48%	74%	61%	67%	67%	85%	74%	71%	82%	65%	67%	74%	78%	74%	61%	54%
87.1%	95%	84%	86%	95%	95%	90%	90%	86%	97%	97%	75%	86%	87%	86%	86%	86%	80%	82%	75%	95%	76%

Model Similarity Dendrogram

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