	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	6th 75.7%	7th 75.4%	1st 77.3%	2nd 77.0%	18th 73.2%	9th 75.2%	11th 75.0%	19th 71.5%	13th 74.1%	8th 75.3%	3rd 76.8%	20th 70.3%	12th 74.5%	10th 75.0%	4th 76.7%	5th 76.0%	17th 73.4%	21st 69.3%	14th 73.8%	16th 73.5%	15th 73.6%
67.4%	62%	66%	77%	67%	65%	67%	72%	64%	75%	72%	71%	72%	64%	76%	63%	68%	49%	69%	63%	65%	69%
51.2%	46%	49%	51%	54%	49%	60%	43%	41%	39%	51%	53%	57%	54%	54%	62%	46%	49%	44%	56%	71%	46%
59.9%	63%	57%	63%	61%	51%	65%	55%	63%	51%	61%	63%	59%	58%	60%	53%	62%	63%	55%	53%	90%	52%
75.0%	75%	76%	76%	69%	75%	70%	69%	78%	79%	71%	78%	66%	80%	78%	86%	78%	75%	80%	69%	78%	70%
75.3%	77%	75%	80%	80%	69%	79%	78%	74%	70%	70%	77%	80%	74%	77%	85%	80%	71%	78%	73%	75%	60%
84.3%	75%	77%	75%	78%	71%	86%	89%	84%	81%	85%	83%	96%	92%	96%	85%	72%	97%	93%	91%	81%	83%
80.8%	83%	78%	84%	89%	88%	73%	83%	87%	83%	79%	79%	79%	84%	82%	73%	83%	69%	80%	81%	87%	73%
87.2%	87%	94%	84%	90%	80%	67%	96%	85%	92%	82%	97%	97%	94%	92%	92%	89%	89%	68%	85%	89%	82%
82.5%	79%	80%	91%	90%	82%	93%	97%	89%	91%	83%	74%	91%	84%	88%	69%	71%	77%	80%	86%	69%	69%
69.3%	75%	73%	68%	69%	68%	77%	66%	64%	69%	69%	70%	68%	69%	74%	73%	73%	63%	66%	74%	64%	64%
76.2%	84%	84%	85%	84%	63%	95%	76%	85%	78%	67%	83%	80%	67%	69%	76%	73%	74%	50%	81%	78%	68%
86.2%	89%	83%	95%	92%	88%	85%	87%	96%	90%	83%	88%	80%	86%	85%	88%	90%	78%	68%	88%	84%	88%
65.3%	57%	69%	58%	75%	61%	84%	64%	50%	59%	70%	73%	57%	61%	63%	61%	69%	65%	62%	77%	65%	71%
73.1%	76%	80%	75%	67%	70%	72%	78%	69%	74%	71%	79%	72%	71%	85%	74%	75%	62%	75%	79%	69%	62%
84.1%	90%	89%	87%	90%	83%	85%	82%	72%	79%	88%	89%	73%	82%	84%	89%	85%	85%	89%	82%	75%	88%
85.9%	83%	90%	87%	81%	80%	80%	86%	90%	83%	94%	89%	91%	90%	87%	87%	92%	78%	80%	87%	81%	87%
55.8%	63%	62%	79%	66%	56%	52%	57%	40%	60%	48%	54%	46%	44%	49%	66%	67%	41%	58%	51%	49%	64%
84.6%	91%	84%	85%	90%	87%	70%	79%	84%	85%	78%	85%	83%	84%	82%	84%	88%	88%	91%	88%	79%	91%
43.7%	57%	28%	49%	49%	61%	36%	43%	42%	41%	56%	49%	12%	51%	31%	74%	58%	36%	25%	25%	40%	54%
78.6%	78%	78%	74%	74%	80%	71%	78%	77%	84%	78%	85%	73%	77%	85%	79%	78%	85%	75%	77%		87%
65.1%	66%	65%	70%	63%	68%	75%	63%	55%	61%	68%	70%	61%	66%	69%	60%	56%	58%	65%	72%	73%	63%
60.9%	58%	59%	58%	59%	58%	79%	55%	47%	58%	66%	61%	47%	56%	66%	70%	59%	63%	54%	67%	73%	66%
66.9%	64%	63%	63%	62%	75%	69%	64%	71%	70%	64%	74%	53%	76%	76%	66%	65%	78%	61%	58%	69%	64%
74.9%	83%	80%	78%	81%	79%	79%	63%	68%	73%	83%	76%	59%	74%	73%	83%	72%	69%	74%	73%	75%	78%
73.9%	72%	90%	79%	72%	71%	76%	78%	70%	69%	70%	83%	76%	75%	86%	71%	74%	62%	66%	80%	72%	60%
75.0%	64%	86%	75%	74%	75%	96%	72%	63%	69%	78%	81%	81%	68%	84%	78%	79%	80%	70%	72%	65%	65%
72.3%	75%	74%	77%	79%	75%	61%	72%	73%	70%	76%	71%	74%	76%	68%	73%	76%	71%	66%	71%	70%	70%
79.9%	79%	82%	83%	78%	74%	74%	74%	74%	78%	77%	81%	86%	83%	84%	80%	84%	80%	88%	78%	80%	80%
62.0%	70%	70%	70%	72%	68%	59%	68%	59%	60%	55%	65%	53%	56%	62%	61%	62%	61%	58%	63%	56%	53%
70.5%	79%	65%	79%	79%	77%	64%	79%	74%	67%	73%	72%	65%	67%	61%	77%	69%	66%	66%	59%	68%	74%
69.1%	72%	66%	70%	73%	73%	76%	57%	57%	64%	72%	76%	56%	70%	65%	74%	74%	74%	73%	73%	62%	75%
77.9%	74%	78%	71%	85%	85%	69%	80%	71%	85%	74%	71%	76%	76%	75%	80%	79%	83%	72%	83%	84%	84%
61.9%	68%	62%	68%	55%	55%	70%	59%	68%	55%	66%	68%	64%	63%	65%	59%	60%	59%	67%	57%	56%	56%
77.2%	84%	79%	76%	85%	86%	65%	83%	80%	90%	79%	73%	64%	70%	63%	86%	84%	87%	75%	68%	65%	80%
81.3%	87%	77%	91%	91%	50%	81%	92%	87%	92%	91%	85%	50%	86%	72%	91%	87%	92%	75%	64%	86%	80%
75.6%	77%	81%	83%	70%	68%	85%	74%	71%	69%	71%	79%	79%	78%	85%	68%	75%	83%	68%	84%	71%	69%
76.4%	78%	76%	76%	78%	89%	84%	67%	57%	71%	77%	81%	65%	79%	82%	76%	84%	88%	63%	78%	76%	80%
79.6%	88%	76%	90%	90%	86%	84%	96%	83%	82%	93%	80%	62%	79%	62%	77%	87%	64%	71%	72%	55%	95%
81.0%	81%	87%	86%	87%	74%	89%	76%	68%	76%	86%	87%	73%	73%	86%	88%	77%	83%	67%	87%	79%	90%
95.1%	90%	96%	90%	97%	97%	88%	99%	90%	97%	92%	90%	95%	95%	93%	97%	98%	99%	99%	99%	98%	98%
78.6%	86%	80%	86%	85%	58%	68%	88%	88%	84%	87%	87%	64%	88%	66%	86%	87%	87%	33%	71%	85%	87%
86.9%	91%	84%	91%	86%	89%	84%	91%	86%	89%	97%	83%	98%	90%	91%	81%	88%	80%	80%	86%	83%	77%
91.2%	80%	93%	90%	95%	90%	90%	95%	81%	94%	89%	91%	90%	92%	95%	99%	95%	94%	82%	94%	95%	92%

Model Similarity Dendrogram

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