	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	8th 71.6%	13th 70.6%	3rd 73.6%	2nd 74.2%	17th 68.1%	15th 70.3%	1st 74.9%	11th 70.8%	7th 72.1%	6th 72.8%	16th 68.6%	21st 66.5%	9th 71.3%	20th 67.3%	5th 73.1%	4th 73.2%	10th 71.2%	18th 67.7%	19th 67.5%	14th 70.4%	12th 70.7%
87.4%	92%	87%	92%	86%	94%	82%	94%	85%	82%	92%	82%	77%	92%	92%	100%	92%	88%	74%	82%	82%	89%
56.0%	48%	55%	65%	62%	34%	70%	55%	54%	54%	50%	58%	87%	55%	70%	52%	50%	56%	44%	61%	46%	49%
73.5%	74%	74%	78%	74%	58%	100%	100%	67%	66%	74%	68%	68%	68%	68%	74%	74%	74%	68%	68%	74%	74%
77.0%	80%	72%	77%	86%	75%	73%	80%	86%	79%	84%	79%	75%	75%	78%	77%	61%	77%	76%	79%	75%	72%
68.4%	70%	64%	70%	70%	64%	64%	70%	78%	66%	72%	64%	64%	64%	64%	70%	78%	76%	64%	64%	64%	76%
77.2%	78%	63%	68%	68%	73%	89%	86%	76%	81%	78%	78%	73%	89%	83%	72%	74%	89%	72%	76%	78%	78%
89.1%	92%	100%	90%	92%	86%	89%	87%	87%	90%	100%	93%	87%	100%	87%	77%	86%	93%	89%	86%	92%	69%
62.6%	67%	61%	63%	63%	62%	55%	54%	74%	57%	67%	54%	49%	67%	68%	74%	74%	60%	60%	59%	59%	67%
76.7%	69%	75%	74%	79%	88%	68%	78%	83%	78%	76%	82%	67%	76%	75%	82%	81%	77%	76%	70%	72%	85%
72.0%	75%	65%	72%	76%	75%	75%	68%	70%	75%	72%	75%	78%	75%	75%	68%	71%	65%	61%	75%	75%	71%
46.8%	48%	49%	57%	52%	32%	54%	57%	48%	46%	43%	49%	48%	38%	43%	46%	48%	38%	37%	49%	58%	43%
68.4%	75%	62%	69%	69%	65%	60%	68%	77%	72%	72%	69%	65%	72%	65%	68%	71%	61%	68%	65%	74%	69%
67.4%	66%	72%	77%	70%	61%	68%	72%	61%	60%	68%	61%	68%	72%	61%	76%	73%	63%	63%	65%	66%	72%
70.9%	76%	71%	66%	74%	68%	79%	66%	68%	66%	77%	68%	87%	75%	68%	68%	65%	63%	68%	68%	79%	68%
52.2%	52%	48%	47%	52%	40%	63%	64%	47%	64%	58%	40%	40%	58%	40%	53%	53%	82%	67%	40%	48%	40%
79.8%	86%	86%	86%	77%	82%	72%	80%	82%	75%	81%	81%	71%	86%	71%	86%	85%	86%	65%	75%	76%	87%
63.4%	66%	67%	68%	68%	68%	51%	60%	46%	66%	67%	68%	51%	56%	57%	75%	64%	67%	67%	68%		68%
71.1%	68%	63%	75%	75%	79%	66%	74%	70%	71%	74%	65%	67%	70%	61%	79%	68%	73%	79%	64%	73%	79%
44.3%	40%	34%	40%	40%	62%	34%	40%	48%	44%	45%	46%	33%	40%	40%	50%	60%	58%	39%	37%	59%	42%
76.9%	79%	66%	77%	77%	75%	78%	86%	78%	81%	80%	62%	69%	80%	79%	81%	80%	81%	80%	79%	71%	76%
76.7%	77%	76%	74%	80%	73%	77%	72%	76%	74%	80%	72%	71%	92%	68%	79%	85%	82%	84%	72%	71%
80.8%	78%	83%	78%	78%	77%	86%	78%	87%	83%	83%	78%	73%	83%	80%	78%	89%	87%	75%	86%	78%	79%
80.1%	79%	89%	82%	88%	79%	83%	77%	80%	88%	72%	76%	75%	69%	69%	89%	89%	81%	71%	88%	75%	83%
62.1%	60%	52%	55%	71%	61%	61%	74%	61%	67%	76%	61%	61%	71%	61%	55%	55%	61%	67%	61%	61%	52%
73.7%	75%	75%	75%	72%	71%	74%	75%	76%	75%	75%	71%	74%	75%	75%	70%	81%	75%	76%	71%	71%	66%
69.9%	64%	71%	79%	67%	72%	66%	74%	60%	64%	70%	79%	81%	64%	58%	76%	73%	74%	60%	75%	77%	64%
75.4%	81%	65%	82%	82%	82%	65%	81%	85%	78%	75%	68%	60%	82%	71%	83%	68%	81%	80%	75%	80%	60%
71.3%	77%	79%	68%	74%	76%	71%	73%	76%	79%	87%	78%	36%	76%	65%	76%	76%	68%	71%	57%	67%	68%
76.8%	90%	81%	72%	81%	75%	72%	88%	75%	77%	75%	75%	75%	75%	75%	75%	74%	77%	75%	75%	75%	75%
66.2%	71%	64%	66%	69%	64%	58%	68%	66%	68%	68%	54%	61%	66%	58%	71%	73%	62%	70%	54%	69%	90%
79.5%	83%	77%	94%	92%	90%	94%	94%	69%	86%	80%	61%	61%	88%	61%	92%	80%	71%	76%	61%	79%	81%
77.8%	68%	68%	91%	91%	68%	68%	100%	100%	100%	84%	68%	68%	68%	68%	84%	84%	68%	68%	68%	68%	84%
73.5%	74%	74%	78%	74%	58%	100%	100%	67%	66%	74%	68%	68%	68%	68%	74%	74%	74%	68%	68%	74%	74%
76.3%	84%	72%	74%	84%	65%	61%	75%	79%	72%	84%	71%	71%	78%	76%	84%	82%	81%	79%	69%	77%	84%
55.6%	56%	67%	72%	72%	42%	62%	42%	56%	50%	42%	42%	85%	60%	42%	56%	67%	50%	58%	43%	31%	72%
68.4%	70%	69%	68%	72%	72%	60%	63%	73%	75%	77%	74%	70%	65%	65%	68%	73%	63%	63%	64%	66%	67%
54.7%	47%	61%	56%	56%	61%	58%	56%	33%	56%	52%	61%	61%	52%	61%	48%	49%	52%	61%	56%	61%	50%
82.3%	94%	100%	100%	89%	93%	88%	100%	72%	92%	89%	89%	64%	83%	64%	82%	81%	70%	54%	64%	83%	78%
69.7%	74%	75%	83%	76%	61%	63%	72%	64%	70%	68%	83%	53%	70%	71%	70%	73%	64%	66%	63%	69%	75%
67.0%	58%	58%	74%	74%	58%	58%	89%	86%	89%	69%	58%	58%	58%	58%	69%	69%	69%	58%	58%	69%	69%
63.2%	66%	75%	69%	69%	56%	57%	66%	69%	61%	58%	57%	55%	55%	57%	61%	65%	63%	62%	72%	65%	69%
76.7%	76%	78%	78%	78%	64%	62%	79%	74%	75%	75%	84%	75%	79%	86%	78%	85%	78%	73%	79%	79%	75%
85.2%	75%	94%	84%	90%	71%	88%	85%	75%	84%	88%	81%	81%	82%	92%	97%	94%	84%	81%	92%	90%	81%

Model Similarity Dendrogram

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