	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	2nd 71.8%	1st 72.4%	3rd 71.5%	4th 71.3%	15th 65.0%	13th 66.1%	6th 70.7%	7th 69.1%	8th 68.7%	14th 65.4%	5th 70.9%	19th 62.6%	9th 68.7%	9th 68.7%	12th 67.1%	11th 68.0%	17th 64.1%	18th 64.0%	16th 64.4%	20th 59.4%	21st 53.5%
68.2%	72%	71%	80%	74%	72%	57%	68%	69%	64%	73%	64%	58%	68%	67%	72%	72%	67%	61%	61%	85%	58%
68.8%	68%	78%	68%	77%	48%	77%	75%	47%	57%	67%	78%	79%	77%	79%	54%	63%	65%	62%	74%	84%	67%
86.6%	84%	75%	84%	92%	84%	81%	78%	100%	78%	92%	92%	92%	92%	78%	92%	84%	84%	95%	78%	92%	92%
69.3%	75%	62%	64%	64%	77%	64%	75%	77%	75%	77%	61%	61%	63%	63%	75%	75%	77%	63%	62%	61%	84%
73.7%	80%	80%	86%	89%	70%	92%	86%	78%	81%	57%	67%	80%	57%	73%	86%	72%	67%	66%	81%	65%	34%
80.5%	74%	79%	74%	84%	84%	83%	81%	100%	83%	81%	88%	83%	88%	88%	74%	74%	83%	73%	78%	68%	71%
62.9%	81%	80%	69%	65%	52%	49%	76%	75%	72%	54%	76%	68%	43%	65%	38%	68%	68%	77%	65%	43%	36%
65.4%	70%	70%	60%	67%	66%	55%	71%	77%	63%	66%	68%	61%	66%	55%	70%	61%	70%	71%	59%	64%	63%
83.2%	78%	96%	87%	91%	92%	66%	76%	92%	85%	83%	86%	73%	92%	100%	77%	78%	93%	93%	87%	79%	44%
60.0%	67%	67%	62%	67%	61%	68%	55%	49%	57%	61%	67%	67%	55%	67%	55%	55%	45%	52%	67%	43%	73%
66.6%	79%	84%	79%	78%	54%	79%	72%	74%	78%	62%	77%	62%	62%	80%	79%	62%	51%	54%	0%	79%	53%
68.7%	69%	71%	71%	64%	80%	71%	71%	70%	64%	66%	78%	72%	80%	71%	66%	64%	60%	55%	60%	71%	69%
63.3%	56%	71%	64%	64%	74%	69%	60%	57%	62%	64%	71%	60%	64%	75%	65%	66%	68%	68%	79%	52%	21%
56.4%	68%	69%	70%	70%	36%	60%	70%	63%	68%	42%	68%	69%	38%	68%	48%	61%	47%	62%	41%	32%	34%
71.1%	76%	73%	75%	75%	62%	68%	73%	62%	73%	73%	75%	77%	73%	76%	74%	73%	66%	70%	63%	65%
68.0%	81%	78%	81%	60%	64%	47%	71%	74%	71%	81%	65%	52%	85%	75%	80%	78%	72%	65%	55%	46%	46%
57.8%	71%	68%	80%	65%	37%	52%	64%	53%	57%	53%	65%	39%	39%	65%	71%	71%	54%	33%	50%	57%	69%
55.2%	68%	53%	55%	73%	80%	34%	42%	59%	51%	51%	42%	43%	68%	47%	71%	62%	67%	54%	39%	55%	45%
57.7%	70%	49%	59%	64%	81%	42%	70%	58%	52%	58%	58%	29%	77%	52%	73%	79%	48%	45%	35%	58%	54%
68.3%	72%	74%	77%	68%	52%	80%	86%	75%	79%	55%	79%	50%	71%	69%	78%	79%	66%	67%	69%	47%	41%
52.8%	52%	51%	54%	42%	39%	64%	63%	49%	61%	48%	55%	55%	63%	61%	42%	50%	45%	41%	55%	68%	51%
71.7%	71%	83%	83%	74%	74%	83%	77%	62%	72%	71%	89%	64%	77%	83%	60%	60%	70%	55%	75%	74%	48%
64.3%	60%	64%	61%	67%	64%	70%	73%	78%	78%	63%	61%	55%	67%	64%	63%	61%	61%	55%	63%		57%
73.0%	82%	83%	73%	82%	75%	82%	71%	68%	73%	82%	83%	33%	75%	84%	80%	73%	73%	66%	79%	79%	38%
62.6%	72%	83%	76%	71%	39%	71%	76%	68%	77%	45%	84%	45%	49%	68%	61%	56%	55%	72%	68%	44%	35%
53.9%	50%	63%	62%	51%	46%	57%	62%	51%	56%	57%	55%	59%	55%	62%	41%	52%	44%	61%	58%	55%	35%
75.2%	77%	79%	79%	77%	80%	58%	76%	80%	76%	77%	63%	69%	79%	75%	86%	85%	79%	71%	69%	63%	81%
65.8%	72%	72%	68%	71%	77%	46%	68%	75%	72%	71%	68%	61%	65%	51%	66%	69%	72%	56%	53%	58%	71%
70.7%	80%	93%	80%	80%	93%	61%	78%	65%	64%	64%	64%	64%	64%	64%	69%	69%	64%	57%	64%	69%	79%
61.8%	68%	74%	67%	68%	66%	48%	55%	65%	78%	45%	69%	34%	67%	45%	74%	64%	61%	63%	72%	48%	66%
77.8%	73%	76%	78%	82%	92%	100%	79%	81%	70%	51%	82%	82%	85%	76%	70%	76%	91%	77%	91%	83%	38%
71.5%	67%	83%	74%	67%	74%	77%	80%	59%	80%	67%	67%	67%	67%	80%	67%	74%	74%	63%	80%	67%	67%
58.0%	64%	50%	58%	64%	58%	55%	52%	71%	52%	64%	64%	64%	64%	52%	64%	58%	58%	67%	52%	24%	64%
68.8%	76%	71%	77%	76%	59%	66%	78%	72%	76%	69%	75%	51%	72%	73%	72%	78%	69%	76%	63%	51%	45%
63.9%	79%	76%	65%	73%	24%	79%	64%	79%	65%	65%	65%	58%	68%	71%	51%	50%	65%	52%	66%
53.0%	50%	57%	62%	54%	34%	62%	56%	54%	44%	57%	58%	62%	58%	64%	50%	54%	41%	52%	61%	51%	31%
54.9%	54%	56%	58%	58%	64%	64%	58%	40%	54%	56%	60%	55%	60%	60%	39%	58%	61%	54%	61%	54%	29%
71.3%	90%	72%	84%	84%	81%	90%	90%	77%	90%	84%	71%	63%	77%	64%	67%	70%	44%	51%	81%	51%	17%
78.4%	83%	89%	88%	88%	67%	67%	83%	86%	86%	64%	83%	84%	85%	69%	78%	85%	80%	78%	86%	72%	45%
83.7%	92%	75%	84%	92%	84%	81%	78%	100%	78%	92%	92%	92%	92%	78%	92%	84%	84%	95%	78%	46%	68%
70.4%	91%	75%	78%	78%	61%	68%	79%	68%	73%	87%	80%	92%	82%	71%	72%	74%	28%	76%	68%	20%	58%
54.8%	61%	60%	53%	53%	51%	46%	62%	60%	55%	61%	56%	35%	56%	57%	56%	58%	57%	51%	53%	51%	58%
65.8%	65%	80%	69%	65%	65%	54%	61%	55%	55%	55%	78%	74%	69%	69%	69%	71%	61%	76%	69%	61%	60%

Model Similarity Dendrogram

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