	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	6th 67.8%	4th 68.4%	1st 69.5%	14th 65.7%	16th 65.3%	19th 63.3%	10th 66.9%	11th 66.3%	9th 67.2%	5th 68.2%	8th 67.3%	18th 64.2%	7th 67.7%	12th 65.9%	2nd 68.9%	3rd 68.5%	13th 65.7%	20th 61.4%	15th 65.5%	17th 64.5%	- -
71.9%	67%	67%	75%	83%	70%	66%	79%	69%	74%	73%	77%	67%	69%	79%	80%	71%	75%	54%	76%	67%
69.4%	65%	65%	66%	69%	31%	69%	64%	71%	71%	66%	74%	79%	74%	80%	72%	75%	83%	62%	72%	80%
73.9%	80%	75%	75%	63%	63%	84%	71%	76%	63%	80%	75%	67%	80%	75%	76%	74%	75%	80%	75%	71%
76.2%	70%	87%	70%	75%	75%	71%	72%	78%	78%	70%	70%	75%	88%	78%	88%	73%	79%	78%	73%	75%
86.4%	78%	98%	78%	84%	92%	85%	84%	92%	95%	94%	94%	80%	87%	92%	92%	79%	91%	67%	82%	84%
91.4%	97%	95%	92%	97%	97%	88%	90%	77%	80%	97%	97%	91%	90%	90%	97%	91%	84%	88%	97%	92%
71.0%	73%	56%	72%	75%	73%	70%	73%	73%	75%	77%	77%	67%	67%	61%	76%	75%	70%	68%	68%	75%
78.3%	75%	84%	81%	81%	82%	82%	77%	72%	84%	59%	86%	86%	86%	86%	76%	63%	68%	67%	86%	86%
75.0%	87%	77%	64%	73%	67%	53%	62%	76%	70%	87%	77%	82%	88%	77%	77%	76%	75%	94%	64%	73%
74.6%	75%	77%	77%	77%	75%	83%	76%	62%	67%	77%	77%	75%	75%	75%	77%	77%	67%	74%	75%	75%
55.0%	64%	58%	60%	64%	29%	64%	64%	61%	60%	43%	60%	64%	43%	53%	50%	50%	44%	44%	66%	60%
63.1%	68%	61%	68%	68%	67%	82%	61%	60%	61%	54%	54%	67%	51%	62%	61%	64%	62%	62%	68%	61%
54.4%	49%	58%	65%	64%	62%	60%	58%	53%	51%	54%	65%	49%	62%	67%	58%	55%	34%	35%	56%	34%
76.2%	70%	87%	87%	87%	70%	53%	87%	66%	83%	90%	90%	64%	87%	58%	79%	85%	74%	62%	79%	66%
50.1%	50%	55%	52%	43%	48%	57%	54%	42%	53%	43%	50%	53%	54%	48%	44%	46%	56%	48%	46%	59%
76.5%	76%	78%	76%	83%	76%	66%	78%	79%	77%	83%	78%	72%	82%	78%	77%	77%	70%	84%	78%	63%
54.4%	53%	52%	56%	70%	55%	53%	50%	58%	55%	50%	60%	49%	51%	57%	60%	55%	55%	44%	57%	48%
64.4%	69%	67%	67%	67%	70%	46%	57%	71%	62%	67%	57%	59%	59%	54%	71%	68%	70%	70%	67%	71%
55.5%	61%	48%	68%	63%	30%	33%	61%	68%	68%	61%	53%	35%	53%	63%	71%	68%	52%	47%	47%	59%
56.8%	73%	66%	68%	68%	73%	37%	56%	60%	63%	70%	37%	37%	69%	35%	64%	69%	48%	52%	54%	37%
65.7%	71%	66%	74%	70%	66%	62%	72%	54%	67%	95%	67%	67%	59%	62%	66%	67%	58%	51%	53%	67%
79.9%	75%	80%	69%	68%	92%	76%	87%	83%	100%	69%	63%	94%	84%	76%	83%	84%	94%	87%	60%	75%
63.4%	77%	68%	77%	77%	59%	50%	67%	59%	58%	67%	67%	28%	58%	50%	65%	68%	72%	67%	67%	67%
59.8%	63%	67%	63%	63%	69%	63%	61%	61%	61%	67%	67%	47%	56%	64%	49%	65%	47%	47%	68%	47%
45.6%	50%	45%	52%	52%	50%	30%	52%	36%	48%	37%	47%	35%	50%	39%	52%	50%	54%	43%	47%	43%
56.3%	46%	62%	54%	56%	68%	64%	59%	47%	53%	59%	59%	60%	55%	62%	42%	57%	53%	58%	54%	57%
71.8%	78%	79%	73%	72%	76%	45%	70%	82%	75%	64%	61%	72%	72%	64%	76%	72%	85%	75%	67%	77%
61.9%	63%	66%	63%	70%	48%	63%	64%	69%	63%	70%	68%	57%	62%	57%	64%	68%	62%	47%	53%	62%
72.4%	68%	72%	77%	77%	68%	68%	71%	68%	68%	90%	72%	72%	67%	68%	72%	82%	74%	75%	67%	72%
68.8%	70%	71%	74%	74%	84%	65%	70%	74%	67%	74%	71%	58%	66%	67%	68%	69%	65%	62%	72%	55%
57.8%	66%	53%	59%	51%	56%	59%	58%	65%	58%	50%	53%	57%	62%	57%	61%	61%	58%	62%	61%	50%
60.6%	58%	69%	63%	0%	75%	54%	67%	62%	75%	58%	63%	71%	58%	63%	67%	67%	63%	58%	63%	58%
51.5%	59%	50%	55%	0%	44%	63%	51%	55%	44%	59%	55%	48%	59%	55%	51%	53%	55%	59%	55%	59%
42.8%	47%	40%	51%	47%	62%	33%	36%	43%	43%	41%	36%	37%	43%	44%	49%	51%	37%	44%	35%	37%
45.9%	46%	53%	53%	53%	22%	45%	37%	57%	37%	37%	46%	43%	46%	46%	48%	58%	46%	43%	53%	49%
72.8%	76%	79%	79%	84%	46%	78%	75%	72%	60%	64%	75%	75%	75%	80%	79%	73%	77%	67%	69%	74%
66.0%	64%	68%	69%	70%	73%	66%	65%	58%	69%	61%	68%	69%	62%	69%	64%	68%	69%	61%	60%	68%
85.0%	78%	92%	85%	91%	96%	86%	78%	85%	87%	96%	97%	71%	96%	81%	85%	82%	71%	69%	81%	92%
72.6%	76%	75%	79%	76%	74%	69%	76%	71%	74%	74%	74%	74%	74%	69%	73%	76%	69%	70%	61%	69%
79.5%	78%	82%	82%	0%	95%	73%	87%	82%	95%	78%	82%	91%	78%	82%	91%	85%	82%	78%	82%	87%
64.3%	67%	66%	73%	75%	47%	87%	65%	71%	60%	75%	76%	67%	66%	67%	68%	61%	64%	13%	65%	53%
71.1%	72%	69%	72%	77%	77%	60%	72%	75%	72%	84%	64%	86%	74%	73%	74%	71%	70%	56%	70%	54%
65.8%	67%	60%	75%	67%	58%	62%	64%	59%	66%	67%	56%	64%	75%	71%	70%	66%	67%	67%	67%	67%

Model Similarity Dendrogram

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