	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	1st 71.5%	3rd 70.4%	2nd 71.0%	4th 70.1%	10th 67.0%	19th 63.1%	13th 66.3%	6th 68.7%	14th 66.1%	9th 67.4%	5th 69.3%	18th 63.3%	11th 66.6%	12th 66.5%	8th 67.5%	7th 67.7%	15th 65.1%	21st 60.9%	17th 64.4%	16th 64.5%	20th 62.8%
83.0%	80%	83%	89%	78%	79%	67%	96%	97%	87%	82%	83%	84%	87%	81%	89%	89%	75%	70%	74%	85%	88%
59.1%	62%	59%	66%	61%	49%	59%	59%	62%	49%	50%	66%	64%	59%	66%	59%	53%	69%	60%	68%	52%	50%
80.7%	78%	85%	81%	86%	83%	91%	76%	86%	77%	86%	81%	91%	85%	76%	81%	86%	72%	70%	76%	66%	81%
46.1%	53%	44%	49%	49%	49%	53%	39%	47%	44%	41%	49%	8%	42%	55%	34%	45%	69%	39%	51%	79%	29%
63.2%	68%	67%	66%	68%	58%	66%	62%	62%	66%	61%	72%	72%	65%	71%	63%	50%	62%	36%	66%	65%	62%
62.9%	69%	66%	66%	71%	71%	50%	65%	65%	65%	70%	56%	71%	66%	50%	60%	71%	62%	59%	50%	50%	67%
65.0%	68%	65%	73%	59%	57%	66%	69%	60%	67%	59%	74%	69%	69%	66%	71%	65%	56%	60%	62%	73%	57%
59.4%	62%	63%	70%	69%	56%	47%	70%	61%	61%	62%	54%	60%	56%	64%	62%	64%	55%	44%	49%	56%	63%
89.1%	91%	98%	93%	98%	86%	72%	77%	95%	85%	90%	93%	92%	90%	94%	90%	85%	92%	90%	93%	87%	80%
41.5%	43%	42%	33%	56%	46%	47%	30%	41%	37%	49%	50%	11%	42%	51%	33%	41%	63%	33%	60%		21%
71.1%	78%	78%	82%	79%	71%	75%	67%	75%	69%	76%	81%	61%	65%	65%	81%	73%	61%	46%	75%	74%	61%
57.4%	74%	75%	46%	63%	72%	57%	53%	63%	56%	64%	67%	54%	53%	67%	52%	68%	41%	42%	60%	40%	38%
51.7%	56%	54%	61%	59%	51%	46%	58%	62%	56%	51%	49%	51%	45%	47%	52%	43%	45%	54%	43%	47%	56%
64.0%	71%	69%	69%	55%	61%	69%	71%	58%	63%	55%	67%	62%	63%	68%	64%	64%	65%	58%	66%	64%	62%
76.2%	85%	77%	77%	64%	75%	78%	70%	79%	73%	80%	79%	69%	77%	81%	81%	80%	80%	62%	79%	76%	78%
56.6%	59%	60%	62%	61%	59%	46%	64%	65%	55%	62%	55%	57%	55%	55%	63%	55%	47%	48%	51%	54%	55%
62.8%	64%	65%	65%	70%	68%	46%	65%	46%	65%	69%	65%	65%	63%	55%	70%	75%	53%	55%	65%	52%	77%
55.7%	63%	60%	67%	70%	68%	34%	49%	55%	53%	60%	57%	53%	55%	48%	58%	63%	44%	48%	52%	62%	50%
71.0%	82%	80%	72%	80%	32%	68%	73%	80%	71%	74%	83%	72%	74%	79%	66%	62%	75%	73%	80%	65%	51%
85.0%	92%	86%	90%	81%	82%	91%	92%	80%	80%	72%	91%	91%	89%	89%	86%	88%	79%	82%	85%	77%	81%
54.9%	55%	59%	65%	62%	62%	40%	62%	64%	62%	53%	57%	57%	57%	48%	53%	54%	44%	46%	40%	54%	58%
71.3%	78%	78%	80%	69%	77%	67%	77%	78%	79%	68%	71%	67%	71%	71%	67%	71%	71%	72%	63%	61%	62%
60.3%	67%	64%	60%	67%	59%	63%	62%	68%	55%	60%	67%	48%	50%	60%	66%	68%	57%	56%	61%	65%	44%
69.3%	79%	76%	77%	71%	67%	77%	67%	74%	71%	66%	70%	55%	67%	70%	68%	61%	73%	54%	64%	73%	76%
55.5%	58%	51%	61%	52%	61%	50%	61%	49%	54%	55%	57%	55%	55%	55%	61%	52%	57%	55%	52%	62%	53%
66.5%	79%	67%	68%	72%	68%	53%	60%	60%	65%	68%	65%	69%	67%	66%	72%	70%	60%	72%	63%	65%	67%
67.8%	74%	72%	76%	79%	73%	54%	62%	69%	70%	71%	61%	69%	69%	59%	74%	75%	60%	73%	59%	54%	71%
68.5%	74%	76%	73%	76%	73%	51%	70%	73%	79%	81%	71%	71%	71%	53%	78%	80%	60%	60%	44%	54%	71%
58.5%	66%	75%	61%	75%	63%	51%	58%	70%	46%	53%	75%	4%	53%	75%	63%	63%	66%	66%	60%		27%
53.9%	58%	60%	55%	60%	81%	46%	43%	45%	47%	55%	56%	59%	46%	43%	52%	55%	58%	60%	55%	49%	48%
68.7%	81%	72%	80%	65%	70%	66%	70%	76%	69%	60%	67%	67%	70%	71%	50%	60%	73%	72%	62%	74%	68%
81.9%	84%	78%	76%	76%	80%	71%	87%	76%	86%	76%	81%	71%	77%	87%	86%	76%	90%	93%	87%	95%	87%
71.0%	67%	76%	77%	77%	74%	82%	67%	77%	68%	77%	72%	82%	76%	67%	63%	75%	64%	61%	67%	57%	64%
66.4%	71%	72%	72%	51%	66%	68%	68%	62%	65%	68%	66%	70%	62%	71%	70%	61%	73%	70%	62%	62%	65%
73.5%	83%	84%	81%	83%	54%	71%	47%	78%	73%	83%	81%	66%	80%	74%	72%	74%	72%	72%	81%	80%	55%
65.5%	70%	68%	74%	67%	55%	65%	70%	80%	62%	67%	63%	61%	67%	66%	57%	65%	64%	66%	63%	59%	66%
68.7%	67%	63%	71%	58%	59%	80%	63%	54%	67%	58%	75%	54%	71%	78%	58%	67%	80%	82%	79%	77%	82%
79.0%	89%	80%	83%	78%	83%	85%	81%	86%	77%	83%	78%	74%	89%	67%	90%	82%	80%	59%	76%	56%	82%
64.2%	72%	67%	65%	77%	73%	41%	73%	74%	67%	75%	65%	70%	71%	55%	77%	72%	50%	67%	45%	45%	48%
93.4%	90%	99%	95%	100%	97%	94%	90%	100%	91%	100%	95%	94%	99%	90%	95%	98%	86%	84%	90%	82%	92%
73.1%	74%	70%	80%	80%	75%	74%	81%	77%	77%	78%	79%	71%	72%	72%	75%	79%	73%	24%	72%	74%	79%
64.3%	64%	64%	68%	64%	63%	63%	72%	68%	68%	63%	64%	67%	64%	68%	65%	70%	56%	54%	64%	60%	61%
67.8%	78%	79%	78%	78%	75%	74%	55%	55%	65%	68%	71%	63%	58%	65%	74%	63%	68%	70%	55%	63%	68%

Model Similarity Dendrogram

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