	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	5th 70.0%	3rd 70.9%	2nd 71.0%	9th 68.6%	18th 64.3%	12th 66.8%	7th 68.8%	14th 65.7%	13th 66.6%	16th 65.0%	1st 72.4%	19th 63.9%	7th 68.8%	6th 69.1%	10th 67.7%	11th 67.6%	15th 65.0%	20th 60.5%	4th 70.6%	17th 64.4%	21st 55.3%
64.2%	67%	65%	72%	63%	72%	56%	80%	65%	74%	63%	67%	55%	63%	67%	57%	58%	49%	49%	66%	70%	70%
60.3%	60%	63%	60%	58%	36%	70%	55%	63%	57%	47%	76%	74%	64%	71%	60%	59%	53%	67%	76%	61%	36%
73.0%	77%	72%	77%	72%	57%	72%	72%	80%	67%	84%	77%	72%	72%	77%	84%	82%	72%	67%	67%	67%	67%
71.6%	83%	83%	64%	64%	78%	79%	83%	69%	74%	63%	64%	63%	64%	63%	75%	77%	65%	64%	83%	64%	81%
75.6%	69%	84%	76%	66%	87%	64%	69%	76%	76%	75%	88%	87%	93%	83%	65%	84%	82%	82%	69%	63%	50%
85.7%	76%	86%	76%	83%	83%	89%	86%	77%	89%	89%	83%	92%	86%	99%	77%	89%	99%	95%	92%	92%	61%
68.5%	75%	77%	77%	71%	54%	70%	75%	75%	70%	69%	75%	70%	77%	80%	75%	73%	64%	37%	73%	38%	63%
77.5%	82%	85%	88%	86%	69%	68%	81%	85%	83%	70%	85%	89%	85%	84%	65%	74%	86%	67%	81%	51%	63%
78.8%	67%	74%	88%	88%	87%	78%	93%	92%	94%	71%	78%	92%	76%	79%	66%		77%	67%	93%	73%	44%
64.2%	66%	66%	58%	66%	64%	77%	58%	57%	75%	64%	63%	63%	64%	71%	58%	63%	58%	54%	66%	64%	73%
70.3%	80%	77%	80%	82%	72%	80%	77%	73%	73%	52%	71%	67%	58%	58%	81%	67%	45%	39%	92%	79%	74%
74.1%	68%	73%	74%	77%	81%	72%	74%	69%	77%	80%	69%	79%	79%	74%	77%	73%	61%	80%	77%	66%	77%
70.1%	67%	83%	86%	67%	74%	71%	67%	70%	78%	61%	88%	73%	74%	73%	67%	62%	83%	44%	76%	83%	25%
44.8%	50%	59%	52%	43%	30%	51%	62%	53%	38%	35%	50%	53%	42%	42%	47%	42%	32%	38%	70%	24%	27%
70.6%	78%	75%	66%	71%	72%	82%	57%	52%	54%	66%	82%	50%	82%	64%	79%	75%	78%	68%	82%	76%	74%
70.0%	77%	74%	77%	69%	48%	63%	82%	79%	74%	71%	79%	56%	80%	82%	73%	69%	62%	51%	84%	55%	65%
70.8%	83%	83%	94%	70%	86%	55%	70%	55%	70%	70%	78%	53%	65%	67%	88%	77%	47%	58%	70%	76%
55.0%	62%	50%	54%	65%	67%	32%	45%	52%	46%	62%	49%	61%	69%	39%	61%	58%	51%	64%	38%	64%	67%
41.9%	41%	30%	54%	41%	63%	39%	53%	33%	41%	33%	47%	41%	42%	24%	64%	75%	37%	33%	20%	36%	33%
70.6%	81%	56%	73%	79%	77%	69%	73%	71%	77%	84%	72%	70%	77%	73%	75%	65%	64%	62%	73%	52%	59%
64.2%	61%	70%	74%	67%	54%	75%	80%	63%	65%	56%	82%	48%	70%	77%	51%	49%	53%	53%	73%	89%	38%
55.9%	48%	67%	68%	59%	55%	74%	52%	46%	59%	39%	74%	43%	51%	71%	60%	44%	71%	57%	74%	38%	24%
56.4%	62%	50%	50%	55%	60%	57%	51%	50%	50%	68%	50%	52%	68%	57%	57%	53%	63%	52%	50%	68%	62%
77.5%	86%	73%	72%	86%	90%	64%	88%	88%	82%	86%	82%	50%	90%	80%	83%	82%	84%	73%	57%	90%	41%
41.8%	43%	57%	50%	28%	32%	49%	48%	48%	45%	32%	59%	45%	39%	45%	28%	48%	24%	33%	61%	39%	25%
56.2%	60%	64%	67%	53%	48%	68%	70%	59%	64%	59%	68%	30%	48%	73%	52%	52%	41%	47%	72%	50%	35%
57.1%	59%	63%	69%	58%	54%	50%	62%	59%	59%	70%	59%	38%	66%	62%	56%	61%	56%	56%	60%	40%	42%
71.7%	80%	81%	79%	77%	62%	52%	80%	75%	63%	78%	80%	70%	79%	64%	70%	69%	68%	70%	69%	65%	74%
74.3%	95%	80%	95%	95%	83%	70%	74%	72%	73%	64%	72%	63%	73%	71%	73%	73%	71%	56%	70%	73%	65%
64.7%	86%	69%	69%	77%	71%	46%	59%	72%	58%	69%	64%	60%	61%	64%	75%	64%	57%	19%	71%	77%	71%
54.9%	54%	55%	54%	54%	59%	65%	45%	42%	44%	42%	69%	62%	52%	61%	57%	65%	61%	69%	60%	66%	17%
54.9%	51%	56%	51%	56%	72%	56%	56%	48%	61%	45%	51%	56%	56%	51%	46%	46%	56%	61%	61%	61%
73.0%	77%	72%	77%	72%	57%	72%	72%	80%	67%	84%	77%	72%	72%	77%	82%	82%	72%	67%	67%	67%	67%
77.5%	82%	79%	79%	82%	65%	76%	82%	84%	75%	82%	79%	82%	83%	74%	82%	77%	81%	74%	67%	68%	74%
64.3%	70%	72%	72%	72%	31%	74%	67%	64%	61%	67%	61%	54%	64%	72%	64%	63%	67%	77%	55%	66%	57%
59.3%	63%	65%	63%	51%	35%	76%	58%	66%	53%	53%	63%	70%	63%	70%	51%	58%	65%	62%	76%	43%	42%
66.9%	65%	75%	65%	58%	83%	83%	56%	41%	54%	58%	83%	49%	55%	64%	76%	72%	82%	72%	76%	79%	59%
85.7%	89%	96%	89%	89%	70%	91%	83%	92%	89%	92%	93%	84%	93%	80%	92%	88%	71%	67%	92%	67%	92%
53.3%	46%	64%	59%	54%	48%	65%	53%	44%	48%	46%	65%	54%	48%	66%	37%	55%	65%	64%	68%	48%	22%
91.8%	89%	94%	89%	94%	89%	94%	94%	85%	100%	82%	89%	94%	94%	89%	82%	83%	94%	100%	100%	100%
74.9%	78%	77%	78%	82%	58%	64%	82%	80%	75%	72%	78%	72%	80%	81%	80%	81%	81%	38%	63%	85%	87%
61.7%	68%	67%	63%	63%	56%	39%	56%	59%	59%	63%	74%	56%	63%	73%	71%	65%	63%	59%	56%	67%	55%
81.5%	88%	88%	77%	88%	74%	74%	77%	62%	72%	78%	100%	83%	77%	79%	94%	88%	86%	88%	88%	70%

Model Similarity Dendrogram

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