	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	4th 71.3%	3rd 71.4%	1st 72.4%	2nd 71.9%	15th 66.2%	19th 65.4%	9th 68.8%	5th 70.5%	10th 68.7%	7th 70.2%	12th 68.0%	13th 66.8%	11th 68.6%	16th 66.1%	6th 70.2%	8th 69.5%	20th 64.6%	21st 63.5%	18th 65.5%	17th 66.0%	14th 66.3%
66.3%	69%	68%	68%	73%	70%	58%	64%	69%	68%	68%	68%	62%	69%	65%	71%	64%	63%	62%	61%	66%	67%
73.2%	81%	69%	84%	76%	46%	77%	73%	77%	71%	83%	76%	70%	77%	70%	84%	61%	73%	75%	70%	61%	83%
90.5%	90%	90%	97%	97%	90%	90%	90%	97%	83%	97%	100%	90%	90%	91%	83%	83%	87%	79%	90%	97%	90%
81.3%	78%	90%	77%	90%	69%	90%	78%	70%	62%	76%	90%	91%	91%	79%	76%	78%	59%	91%	91%	91%	91%
84.0%	81%	84%	81%	80%	87%	76%	81%	86%	94%	86%	86%	86%	86%	89%	74%	82%	86%	74%	81%	95%	89%
81.2%	90%	90%	90%	90%	90%	67%	78%	85%	78%	85%	85%	78%	78%	71%	82%	86%	78%	74%	82%	64%	85%
54.4%	47%	54%	47%	54%	62%	49%	47%	62%	55%	54%	50%	66%	54%	61%	60%	54%	54%	58%	49%	54%	51%
61.0%	67%	67%	61%	67%	79%	41%	65%	60%	55%	67%	53%	58%	67%	53%	65%	64%	61%	57%	49%	68%	58%
70.3%	69%	73%	69%	61%	71%	61%	69%	78%	71%	69%	69%	69%	69%	66%	71%	69%	71%	66%	71%	79%	86%
81.2%	76%	91%	76%	76%	91%	91%	72%	76%	76%	76%	79%	91%	91%	91%	76%	86%	63%	59%	91%	91%	86%
70.0%	78%	75%	78%	77%	59%	79%	78%	74%	74%	63%	67%	72%	55%	67%	74%	66%	55%	59%	88%	79%	52%
71.6%	77%	85%	77%	85%	85%	70%	69%	66%	77%	64%	77%	73%	50%	79%	75%	77%	31%	53%	79%	55%	100%
66.3%	74%	74%	76%	74%	56%	78%	59%	70%	74%	59%	69%	70%	56%	80%	58%	63%	56%	56%	78%	56%	56%
67.9%	70%	70%	70%	70%	70%	76%	61%	70%	66%	70%	70%	72%	54%	67%	66%	70%	63%	66%	66%	73%	65%
79.1%	100%	86%	90%	90%	66%	64%	84%	90%	82%	77%	77%	84%	76%	64%	77%	88%	74%	64%	53%	93%	83%
63.9%	66%	60%	68%	61%	57%	68%	70%	60%	66%	66%	68%	50%	66%	62%	68%	68%	70%	56%	62%	61%	68%
76.8%	79%	75%	75%	90%	75%	64%	75%	78%	79%	78%	79%	69%	78%	78%	76%	75%	68%	74%	76%	85%	87%
34.5%	43%	43%	43%	49%	45%	21%	29%	43%	36%	37%	28%	26%	37%	32%	29%	30%	29%	30%	28%	29%	37%
47.3%	43%	40%	48%	40%	56%	24%	48%	58%	58%	63%	40%	48%	58%	26%	79%	69%	59%	43%	26%	43%	25%
80.6%	80%	90%	76%	80%	59%	75%	85%	84%	90%	90%	77%	75%	90%	79%	80%	86%	75%	82%	90%	75%	75%
63.8%	69%	69%	69%	69%	72%	54%	66%	62%	59%	69%	59%	61%	66%	54%	70%	67%	69%	59%	48%	59%	69%
77.8%	87%	74%	82%	81%	87%	61%	83%	81%	83%	89%	61%	77%	89%	66%	82%	77%	83%	73%	61%	75%	81%
52.4%	55%	44%	50%	50%	80%	75%	56%	54%	50%	55%	66%	66%	54%	77%	38%	38%	38%	34%	71%	28%	22%
47.8%	54%	52%	53%	53%	46%	55%	44%	46%	54%	44%	55%	37%	41%	54%	48%	48%	41%	41%	55%	41%	41%
64.7%	68%	68%	68%	68%	64%	62%	61%	66%	68%	67%	61%	56%	64%	56%	68%	68%	73%	66%	68%	59%	59%
71.6%	69%	85%	69%	62%	45%	80%	72%	63%	72%	77%	85%	72%	69%	82%	75%	71%	72%	62%	85%	69%	67%
60.8%	64%	64%	64%	64%	60%	52%	54%	64%	58%	67%	59%	50%	64%	54%	70%	64%	59%	57%	59%	67%	63%
55.8%	54%	61%	53%	57%	71%	47%	53%	60%	60%	52%	52%	57%	60%	48%	65%	59%	52%	53%	32%	70%	56%
45.1%	45%	62%	64%	64%	50%	46%	51%	44%	44%	30%	44%	50%	30%	37%	57%	57%	30%	32%	44%	22%	44%
56.2%	70%	50%	70%	70%	51%	52%	65%	56%	62%	60%	55%	50%	55%	52%	62%	53%	44%	49%	50%	52%	52%
80.2%	84%	89%	100%	84%	61%	59%	100%	100%	88%	90%	70%	71%	87%	66%	72%	74%	84%	75%	66%	100%	65%
75.0%	76%	76%	68%	76%	76%	76%	76%	68%	83%	68%	66%	76%	76%	74%	83%	83%	78%	83%	76%	68%	68%
49.1%	50%	50%	56%	50%	50%	50%	50%	56%	44%	56%	59%	50%	50%	51%	44%	44%	48%	44%	50%	41%	38%
77.8%	83%	76%	83%	83%	52%	77%	81%	83%	78%	83%	74%	75%	83%	75%	83%	77%	81%	76%	72%		80%
71.8%	72%	68%	76%	76%	44%	77%	67%	91%	63%	67%	63%	70%	75%	67%	78%	100%	93%	75%	44%	67%	75%
76.3%	82%	79%	83%	84%	54%	73%	79%	76%	76%	84%	76%	73%	79%	73%	78%	75%	73%	73%	66%	90%	77%
58.0%	61%	61%	66%	66%	56%	62%	56%	56%	59%	61%	55%	55%	59%	62%	63%	56%	51%	55%	62%	52%	45%
84.4%	78%	87%	88%	84%	73%	84%	97%	88%	88%	88%	84%	85%	84%	76%	88%	92%	85%	74%	85%	82%	82%
70.8%	77%	76%	68%	68%	73%	59%	76%	77%	69%	76%	61%	58%	76%	65%	84%	81%	77%	80%	48%	70%	68%
89.6%	90%	90%	97%	90%	90%	90%	90%	97%	83%	97%	100%	90%	90%	91%	90%	83%	87%	87%	90%	83%	76%
62.6%	72%	60%	76%	72%	69%	63%	67%	67%	58%	72%	72%	51%	63%	53%	66%	66%	63%	62%	56%	25%	61%
82.6%	91%	81%	85%	77%	85%	85%	83%	85%	91%	91%	71%	85%	91%	78%	77%	71%	81%	67%	91%	83%	85%
56.7%	55%	74%	74%	63%	53%	55%	55%	39%	47%	47%	69%	57%	53%	62%	55%	64%	40%	74%	57%	52%	45%

Model Similarity Dendrogram

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