	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	6th 76.5%	5th 77.0%	1st 79.5%	2nd 77.7%	17th 70.2%	15th 71.7%	3rd 77.4%	4th 77.0%	9th 75.0%	10th 74.1%	8th 75.5%	14th 72.5%	7th 75.5%	13th 73.2%	16th 71.7%	11th 73.5%	18th 69.7%	21st 62.0%	12th 73.4%	19th 69.3%	20th 66.0%
80.7%	87%	81%	90%	87%	74%	60%	88%	93%	84%	85%	86%	75%	81%	83%	80%	76%	73%	64%	75%	83%	89%
70.4%	73%	69%	88%	88%	46%	78%	70%	74%	63%	69%	77%	77%	64%	77%	86%	84%	67%	60%	71%	59%	39%
85.4%	93%	86%	93%	93%	84%	93%	80%	76%	76%	96%	86%	80%	80%	83%	87%	99%	86%		83%	86%	67%
86.6%	88%	86%	86%	88%	88%	85%	90%	89%	83%	86%	87%	89%	87%	89%	89%	86%	84%	81%	85%
84.9%	89%	88%	96%	94%	85%	94%	96%	82%	96%	74%	83%	88%	86%	81%	77%	91%	81%	59%	90%	80%	73%
79.2%	75%	81%	77%	83%	79%	84%	81%	91%	85%	78%	79%	74%	84%	74%	73%	79%	76%	91%	75%	67%	77%
77.6%	74%	77%	78%	87%	87%	73%	77%	77%	82%	84%	69%	75%	72%	68%	81%	85%	82%	73%	67%	84%	78%
67.9%	75%	75%	69%	83%	70%	48%	69%	80%	69%	83%	70%	63%	69%	61%	65%	77%	69%	29%	63%	63%	76%
76.5%	68%	67%	81%	74%	65%	80%	92%	83%	84%	68%	79%	92%	78%	81%	68%	75%	70%	81%	82%	73%	66%
87.9%	87%	91%	91%	88%	90%	89%	85%	84%	89%	86%	90%	88%	89%	89%	89%	87%	89%	82%	90%	87%	85%
61.6%	72%	72%	69%	78%	57%	69%	65%	82%	57%	48%	64%	52%	57%		61%	52%	56%	45%	90%		25%
84.0%	80%	86%	85%	86%	81%	86%	85%	78%	87%	81%	82%	84%	88%	88%	84%	86%	82%	80%	84%	87%	83%
65.2%	49%	81%	77%	63%	79%	81%	71%	75%	77%	53%	82%	56%	71%	80%	39%	51%	80%	37%	74%	54%	40%
76.5%	79%	84%	83%	67%	73%	78%	84%	74%	72%	70%	84%	84%	83%	92%	76%	76%	70%	54%	91%	66%	66%
73.0%	77%	78%	84%	81%	75%	63%	78%	82%	76%	74%	64%	83%	76%	67%	71%	67%	62%	72%	65%	75%	62%
72.9%	80%	77%	80%	74%	65%	64%	84%	84%	76%	77%	80%	69%	70%	75%	70%	72%	58%	55%	73%	66%	81%
71.9%	86%	89%		82%	62%	62%	73%	63%	73%	75%	74%	43%	66%	74%	85%	74%	65%	48%	78%	79%	87%
70.5%	84%	75%	84%	81%	78%	45%	63%	79%	69%	81%	65%	62%	73%	51%	84%	77%	67%	45%	65%	76%	76%
50.3%	52%	42%	54%	52%	60%	39%	58%	54%	48%	54%	56%	43%	48%	50%	62%	68%	47%	37%	36%	54%	42%
83.0%	84%	74%	80%	89%	83%	90%	78%	94%	85%	94%	83%	82%	77%	71%	89%	91%	82%	80%	71%	80%	86%
63.9%	65%	68%	79%	59%	53%	62%	80%	69%	68%	62%	73%	68%	66%	70%	46%	61%	56%	52%	61%	60%	64%
72.0%	77%	78%	89%	75%	83%	73%	87%	85%	82%	71%	76%	76%	83%	75%	49%	64%	67%	59%	59%		33%
85.3%	93%	89%	86%	91%	72%	75%	86%	89%	86%	93%	83%	89%	85%	70%	92%	87%	81%	82%	82%	89%	92%
69.1%	63%	88%	70%	70%	71%	91%	73%	73%	71%	63%	88%	59%	79%	79%	60%	71%	44%	61%	78%	53%	47%
74.5%	77%	81%	83%	67%	77%	80%	81%	73%	70%	69%	84%	81%	79%	82%	73%	72%	72%	65%	83%	54%	61%
66.5%	69%	73%	73%	63%	64%	60%	68%	69%	67%	64%	72%	69%	68%	68%	62%	69%	63%	59%	70%	63%	64%
64.7%	79%	70%	77%	81%	78%	30%	56%	67%	61%	76%	49%	56%	70%	38%	79%	67%	66%	67%	56%	66%	70%
69.6%	77%	72%	76%	80%	60%	60%	79%	80%	71%	75%	69%	77%	74%	64%	63%	66%	60%	59%	65%	60%	75%
87.6%	92%	91%	91%	93%	88%	86%	91%	83%	82%	86%	85%	89%	86%	80%	91%	92%	89%	80%	90%	92%	83%
78.3%	84%	82%	88%	92%	72%	75%	79%	82%	78%	87%	80%	73%	81%	73%	83%	77%	80%	47%	73%	84%	75%
67.4%	66%	68%	85%	68%	48%	75%	80%	86%	81%	64%	78%	78%	82%	78%	50%	59%	58%	65%	72%	42%	33%
61.7%	49%	62%	56%	56%	64%	56%	67%	72%	72%	53%	62%	68%	68%	65%		50%	62%	64%	65%	62%	61%
75.2%	83%			83%	75%	83%	71%	66%	66%	86%	76%	70%	70%	73%	76%	89%	76%	75%	73%		62%
77.8%	77%	83%	79%	85%	83%	80%	83%	83%	85%	89%	75%	67%	74%	66%	86%	88%	84%	35%	68%	85%
65.1%	89%	75%	67%	76%	61%	68%	58%	45%	65%	78%	49%	61%	83%	69%	50%	52%	37%	55%	80%	68%	82%
61.1%	58%	68%	63%	57%	37%	71%	61%	60%	65%	51%	77%	70%	66%	72%	46%	49%	78%	58%	69%	53%	55%
60.0%	65%	55%	75%	56%	44%	79%	75%	65%	66%	51%	77%	70%	68%	74%	36%	50%	64%	53%	77%	35%	26%
79.0%	87%	90%	91%	75%	89%	88%	95%	93%	90%	82%	80%	74%	80%	71%	78%	80%	61%	69%	74%	62%	51%
68.6%	80%	76%	80%	80%	31%	63%	81%	74%	74%	72%	75%	75%	78%	66%	61%	69%	57%	53%	58%	71%	67%
66.0%	53%	66%	60%	60%	68%	60%	72%	77%	77%	57%	66%	72%	72%	69%	67%	54%	67%	68%	69%	66%	66%
66.6%	76%	69%	76%	78%	59%	73%	73%	65%	56%	65%	69%	69%	63%	62%	71%	70%	62%	58%	64%	54%
86.9%	96%	93%	92%	94%	90%	57%	82%	86%	81%	94%	87%	74%	90%	93%	91%	91%	90%	83%	85%	86%	90%
80.3%	84%	78%	80%	82%		78%	82%	77%	81%	83%	75%	75%	83%	83%	84%	82%	77%		79%	78%	84%

Model Similarity Dendrogram

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