	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	5th 76.3%	4th 76.4%	1st 77.9%	2nd 77.7%	14th 74.0%	10th 75.6%	8th 76.0%	16th 72.6%	15th 72.9%	9th 75.7%	6th 76.2%	18th 71.3%	12th 74.3%	13th 74.0%	3rd 77.3%	7th 76.1%	19th 70.5%	21st 67.5%	11th 74.9%	20th 69.4%	17th 71.4%
66.1%	63%	59%	71%	67%	60%	72%	72%	66%	65%	67%	69%	57%	61%	72%	71%	64%	63%	70%	63%	65%	71%
51.0%	42%	47%	52%	67%	41%	60%	43%	48%	41%	58%	59%	57%	55%	58%	54%	58%	39%	42%	53%	53%	43%
56.1%	63%	57%	63%	51%	51%	55%	57%	59%	51%	61%	63%	51%	58%	59%	57%	57%	54%	55%	53%	52%	52%
74.8%	78%	69%	76%	72%	82%	71%	76%	74%	80%	76%	84%	68%	78%	72%	74%	81%	76%	73%	76%	65%	70%
73.3%	77%	77%	78%	80%	68%	74%	81%	78%	69%	74%	80%	90%	73%	76%	82%	72%	62%	63%	75%	55%	55%
83.6%	75%	77%	74%	77%	74%	83%	89%	81%	90%	83%	83%	96%	88%	96%	76%	72%	97%	79%	88%	90%	87%
83.2%	83%	88%	88%	86%	84%	84%	89%	85%	83%	86%	87%	90%	82%	79%	87%	83%	71%	82%	87%	71%	72%
88.6%	90%	95%	84%	90%	97%	67%	92%	83%	92%	92%	89%	93%	92%	85%	92%	93%	93%	83%	88%	89%	81%
84.1%	76%	76%	89%	89%	88%	89%	95%	93%	95%	88%	76%	76%	86%	91%	73%	73%	75%	72%	97%	76%	93%
69.8%	68%	77%	75%	75%	68%	79%	69%	66%	68%	73%	68%	68%	68%	68%	71%	66%	63%	64%	68%	68%	75%
77.2%	87%	84%	89%	84%	70%	89%	84%	87%	79%	72%	78%	80%	67%	61%	74%	74%	82%	45%	80%	74%	82%
82.3%	88%	84%	93%	89%	83%	81%	81%	85%	81%	78%	84%	80%	73%	80%	96%	88%	70%	63%	81%	83%	87%
61.4%	54%	70%	72%	72%	69%	78%	62%	51%	57%	58%	63%	56%	57%	70%	64%	65%	51%	51%	68%	51%	51%
83.1%	92%	87%	85%	87%	92%	73%	86%	86%	85%	84%	82%	67%	85%	69%	88%	87%	82%	88%	76%	81%	83%
84.3%	82%	83%	88%	90%	93%	85%	87%	71%	78%	89%	88%	84%	90%	90%	86%	84%	82%	65%	84%	78%	93%
83.5%	83%	79%	85%	81%	79%	85%	91%	81%	81%	85%	87%	74%	83%	82%	91%	91%	75%	88%	87%	81%	84%
55.8%	61%	63%	62%	57%	63%	50%	60%	46%	54%	49%	62%	44%	42%	55%	59%	71%	58%	47%	55%	56%	58%
84.6%	92%	93%	90%	93%	92%	67%	82%	92%	82%	89%	79%	75%	88%	80%	88%	90%	79%	71%	89%	85%	81%
54.4%	60%	57%	57%	49%	72%	43%	60%	59%	53%	63%	50%	33%	59%	42%	78%	59%	58%	47%	34%	60%	49%
77.1%	82%	85%	82%	79%	82%	69%	82%	79%	74%	83%	81%	68%	81%	68%	82%	87%	68%	72%	71%	68%	76%
64.8%	60%	69%	68%	67%	72%	78%	63%	56%	61%	67%	62%	79%	61%	77%	63%	63%	65%	49%	71%	61%	49%
59.4%	56%	58%	58%	64%	49%	79%	52%	48%	53%	58%	71%	69%	57%	65%	68%	56%	51%	42%	71%	63%	59%
68.5%	68%	70%	63%	64%	71%	70%	70%	78%	65%	69%	65%	65%	85%	65%	64%	70%	76%	70%	75%	62%	53%
72.6%	76%	79%	82%	81%	75%	77%	70%	64%	71%	77%	77%	64%	69%	74%	78%	78%	68%	59%	77%	64%	64%
78.4%	79%	84%	93%	83%	85%	81%	87%	69%	84%	81%	91%	51%	85%	67%	83%	83%	71%	78%	75%	74%	63%
72.4%	62%	83%	69%	71%	69%	92%	74%	61%	67%	77%	84%	78%	68%	80%	76%	72%	54%	70%	77%	71%	65%
71.9%	77%	74%	78%	74%	76%	68%	77%	71%	70%	76%	74%	67%	72%	74%	76%	74%	58%	67%	74%	64%	69%
79.0%	79%	83%	84%	80%	83%	75%	79%	75%	76%	82%	82%	84%	83%	76%	81%	78%	81%	83%	81%	72%	63%
63.1%	71%	75%	73%	76%	62%	59%	71%	56%	63%	59%	63%	55%	54%	55%	69%	68%	54%	58%	61%	60%	64%
67.2%	76%	68%	76%	71%	66%	70%	75%	76%	62%	69%	66%	51%	64%	63%	69%	69%	69%	57%	64%	66%	64%
68.3%	73%	65%	68%	76%	69%	76%	57%	60%	65%	69%	70%	73%	68%	69%	74%	74%	60%	56%	72%	65%	75%
78.4%	71%	81%	71%	85%	85%	80%	78%	76%	85%	74%	71%	85%	76%	76%	85%	76%	81%	85%	83%	62%	80%
60.0%	68%	59%	68%	55%	55%	59%	61%	64%	55%	66%	68%	55%	63%	64%	55%	59%	58%	59%	57%	56%	56%
74.4%	87%	73%	79%	84%	69%	67%	71%	77%	72%	77%	70%	68%	72%	66%	81%	79%	78%	77%	66%	72%	77%
79.5%	85%	88%	91%	92%	50%	80%	72%	86%	84%	72%	76%	72%	72%	76%	89%	96%	88%	83%	72%	66%	79%
73.5%	74%	76%	74%	70%	55%	85%	74%	73%	69%	68%	72%	80%	79%	81%	65%	63%	76%	73%	81%	84%	71%
77.0%	87%	75%	76%	78%	84%	80%	66%	56%	65%	80%	84%	85%	76%	81%	83%	84%	77%	74%	77%	74%	76%
77.0%	92%	76%	84%	84%	84%	83%	92%	90%	86%	87%	82%	60%	81%	74%	84%	77%	60%	48%	82%	55%	55%
78.5%	81%	85%	89%	88%	75%	90%	76%	68%	75%	81%	87%	86%	76%	88%	73%	72%	51%	65%	81%	74%	87%
95.3%	95%	96%	90%	97%	97%	99%	97%	95%	97%	92%	90%	97%	95%	95%	97%	99%	100%	97%	99%	80%	97%
82.1%	86%	83%	86%	86%	81%	82%	88%	87%	83%	87%	84%	58%	88%	81%	86%	81%	81%	70%	76%	77%	93%
83.6%	85%	84%	86%	86%	82%	77%	84%	89%	78%	91%	83%	85%	89%	89%	85%	91%	84%	83%	81%	68%	75%
91.0%	97%	94%	92%	95%	81%	89%	95%	76%	89%	86%	91%	94%	97%	95%	96%	96%	93%	78%	94%	92%	92%

Model Similarity Dendrogram

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