	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	3rd 68.7%	1st 69.2%	11th 66.3%	2nd 68.8%	13th 65.9%	16th 63.7%	17th 63.0%	12th 66.0%	10th 66.4%	4th 67.9%	6th 67.4%	19th 61.7%	8th 67.0%	5th 67.6%	9th 66.9%	7th 67.3%	15th 64.8%	21st 61.1%	14th 65.8%	20th 61.7%	18th 62.1%
80.0%	85%	81%	87%	81%	71%	68%	71%	71%	80%	79%	82%	87%	81%	82%	83%	82%	80%	84%	82%	82%	80%
68.5%	68%	66%	67%	65%	59%	68%	69%	71%	69%	67%	75%	74%	74%	67%	69%	65%	66%	59%	74%	75%	71%
70.5%	70%	78%	72%	79%	67%	82%	69%	75%	63%	75%	69%	77%	67%	70%	69%	75%	66%	63%	66%	59%	70%
42.1%	44%	49%	42%	55%	35%	44%	35%	52%	46%	42%	55%	24%	55%	71%	27%	31%	36%	36%	47%	41%	18%
83.2%	84%	88%	77%	79%	80%	86%	72%	76%	75%	87%	95%	89%	93%	86%	75%	82%	90%	82%	88%	90%	74%
59.2%	59%	63%	61%	60%	68%	58%	63%	63%	64%	64%	52%	52%	55%	55%	61%	61%	59%	61%	52%	54%	59%
64.1%	71%	64%	63%	69%	63%	63%	66%	63%	64%	64%	63%	63%	64%	49%	68%	68%	70%	65%	61%	69%	56%
68.8%	77%	64%	59%	71%	71%	49%	64%	73%	78%	71%	65%	71%	69%	77%	73%	72%	68%	76%	59%	71%	66%
80.6%	87%	92%	68%	82%	95%	62%	74%	68%	74%	95%	84%	90%	78%	84%	91%	90%	88%	74%	74%		62%
33.7%	34%	39%	33%	46%	42%	36%	38%	43%	39%	34%	48%	11%	34%	42%	26%	34%	27%	22%	42%	23%	15%
80.9%	84%	87%	86%	89%	86%	79%	83%	84%	86%	93%	74%	60%	86%	82%	76%	89%	61%	65%	86%	82%	81%
45.3%	50%	55%	49%	57%	56%	40%	38%	45%	52%	48%	44%	18%	49%	56%	48%	48%	47%	35%	51%	33%	33%
63.2%	55%	64%	69%	66%	68%	77%	56%	51%	57%	60%	69%	68%	60%	69%	60%	58%	70%	57%	77%	55%	62%
61.7%	60%	59%	63%	61%	54%	61%	65%	61%	62%	58%	65%	61%	62%	65%	61%	59%	60%	53%	61%	75%	70%
74.9%	84%	77%	74%	70%	72%	80%	60%	69%	70%	78%	75%	59%	72%	82%	79%	76%	85%	61%	74%	91%	84%
67.2%	78%	67%	75%	78%	63%	53%	56%	71%	70%	69%	69%	69%	62%	70%	75%	73%	63%	68%	62%	58%	63%
60.0%	63%	66%	66%	65%	80%	50%	50%	50%	65%	63%	54%	52%	63%	57%	75%	66%	63%	40%	50%	59%	64%
68.4%	81%	70%	74%	80%	81%	45%	63%	66%	71%	67%	69%	69%	69%	51%	83%	76%	61%	72%	64%	62%	63%
57.1%	65%	62%	57%	64%	41%	53%	63%	66%	59%	59%	52%	59%	64%	54%	60%	56%	29%	58%	62%	68%	49%
76.8%	78%	78%	72%	74%	79%	77%	82%	77%	79%	86%	70%	77%	80%	70%	74%	77%	78%	74%	79%	77%	75%
69.9%	68%	71%	70%	70%	70%	71%	63%	68%	70%	73%	71%	70%	67%	78%	71%	64%	65%	71%	72%	74%	71%
75.3%	83%	78%	83%	82%	79%	70%	79%	82%	76%	78%	71%	74%	73%	67%	75%	76%	70%	74%	65%	78%	69%
67.9%	77%	71%	71%	71%	79%	67%	62%	70%	77%	68%	71%	34%	54%	72%	77%	75%	71%	72%	71%	72%	44%
63.8%	66%	70%	63%	63%	64%	63%	63%	65%	63%	69%	70%	56%	64%	71%	69%	66%	75%	61%	80%	10%	69%
70.6%	67%	77%	78%	74%	68%	74%	76%	66%	71%	68%	78%	74%	69%	77%	58%	59%	67%	61%	66%	77%	77%
64.0%	63%	62%	69%	58%	55%	75%	52%	43%	60%	72%	69%	63%	63%	74%	63%	53%	77%	61%	72%	66%	74%
69.1%	62%	64%	64%	60%	67%	73%	65%	53%	67%	69%	83%	71%	71%	83%	60%	72%	82%	78%	78%	58%	72%
55.1%	58%	63%	50%	63%	76%	46%	61%	69%	58%	56%	42%	52%	61%	46%	64%	64%	50%	47%	44%	52%	36%
34.8%	42%	46%	35%	45%	38%	24%	45%	32%	35%	23%	56%	8%	35%	49%	34%	44%	17%	30%	35%	35%	22%
53.3%	56%	54%	57%	56%	40%	45%	37%	52%	48%	56%	64%	57%	49%	53%	52%	55%	63%	70%	66%	46%	44%
61.3%	64%	71%	60%	60%	60%	60%	58%	59%	65%	65%	69%	60%	64%	68%	68%	69%	62%	53%	73%	10%	70%
58.7%	61%	51%	57%	50%	61%	47%	59%	54%	66%	54%	60%	52%	61%	59%	66%	54%	63%	66%	63%	69%	59%
80.4%	76%	89%	82%	89%	78%	93%	80%	86%	73%	86%	79%	87%	78%	80%	73%	86%	79%	73%	76%	66%	79%
66.0%	68%	63%	66%	69%	64%	61%	70%	69%	68%	69%	61%	61%	69%	56%	67%	66%	69%	69%	62%	70%	68%
57.3%	61%	74%	54%	62%	53%	54%	37%	60%	57%	51%	66%	54%	74%	73%	52%	57%	54%	54%	65%	49%	42%
56.9%	65%	58%	61%	62%	50%	62%	59%	65%	54%	59%	56%	60%	56%	62%	57%	48%	55%	53%	49%	48%	56%
70.0%	77%	74%	69%	69%	71%	68%	68%	71%	74%	74%	69%	72%	71%	69%	71%	68%	63%	61%	70%	69%	73%
79.7%	84%	77%	81%	81%	87%	79%	82%	91%	81%	91%	75%	62%	91%	69%	87%	90%	75%	67%	65%	72%	86%
55.1%	61%	60%	52%	59%	62%	49%	60%	64%	52%	62%	47%	57%	62%	47%	62%	61%	46%	51%	43%	52%	48%
80.8%	78%	89%	82%	89%	78%	93%	80%	86%	73%	86%	79%	87%	78%	80%	79%	86%	77%	73%	76%	69%	79%
74.8%	81%	81%	83%	83%	48%	82%	77%	84%	78%	81%	77%	71%	77%	75%	81%	82%	81%	19%	73%	74%	82%
72.9%	75%	76%	69%	69%	79%	71%	69%	69%	80%	73%	73%	62%	80%	80%	73%	76%	73%	75%	76%	70%	63%
81.1%	82%	86%	83%	83%	77%	82%	68%	86%	85%	79%	83%	79%	79%	79%	86%	85%	85%	85%	79%	80%	72%

Model Similarity Dendrogram

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