	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 76.5%	6th 76.2%	2nd 77.8%	1st 78.0%	14th 73.6%	10th 75.7%	7th 75.9%	18th 71.1%	15th 73.4%	9th 75.7%	8th 75.9%	16th 72.1%	13th 74.4%	12th 74.7%	4th 76.7%	3rd 77.0%	20th 70.0%	21st 67.9%	11th 75.5%	17th 71.6%	19th 70.9%
64.2%	62%	59%	69%	67%	63%	70%	72%	57%	68%	64%	74%	51%	63%	72%	69%	63%	45%	62%	65%	63%	71%
50.8%	45%	47%	51%	70%	26%	51%	43%	47%	40%	58%	54%	59%	55%	58%	63%	53%	50%	37%	53%	46%	61%
56.3%	63%	57%	63%	51%	51%	55%	57%	59%	51%	60%	62%	51%	51%	60%	57%	55%	57%	57%	53%	61%	51%
75.3%	73%	69%	76%	70%	77%	71%	78%	75%	80%	76%	82%	68%	75%	72%	86%	79%	74%	72%	77%	68%	83%
76.2%	76%	77%	81%	80%	68%	79%	78%	78%	71%	74%	80%	90%	79%	76%	82%	78%	66%	70%	77%	67%	74%
84.0%	78%	77%	74%	77%	76%	83%	89%	86%	89%	83%	85%	96%	91%	97%	79%	80%	83%	79%	83%	90%	88%
84.7%	85%	88%	88%	89%	84%	84%	89%	85%	85%	84%	85%	90%	82%	90%	87%	83%	86%	83%	84%	78%	69%
89.4%	90%	95%	85%	90%	91%	67%	92%	89%	92%	92%	88%	95%	97%	84%	89%	91%	97%	90%	91%	92%	81%
83.9%	78%	76%	86%	89%	89%	89%	95%	91%	91%	88%	84%	76%	86%	89%	73%	76%	76%	96%	96%	69%	69%
70.8%	68%	77%	75%	75%	68%	79%	69%	67%	68%	71%	68%	68%	68%	68%	69%	71%	77%	68%	68%	68%	77%
77.4%	83%	84%	90%	84%	78%	86%	84%	87%	81%	63%	73%	82%	72%	61%	75%	75%	61%	65%	89%	84%	68%
80.9%	89%	84%	87%	89%	81%	81%	81%	80%	89%	72%	80%	80%	67%	78%	83%	85%	54%	76%	86%	90%	87%
59.5%	56%	70%	72%	72%	61%	74%	62%	51%	58%	58%	66%	54%	57%	70%	51%	63%	51%	30%	72%	51%	51%
81.5%	89%	87%	85%	87%	88%	73%	86%	78%	74%	87%	82%	57%	85%	67%	90%	88%	70%	81%	81%	84%	92%
84.2%	94%	83%	90%	86%	89%	87%	90%	71%	78%	86%	90%	84%	87%	88%	88%	82%	77%	79%	82%	78%	80%
83.8%	84%	79%	87%	81%	87%	87%	91%	82%	80%	87%	88%	75%	85%	89%	87%	91%	77%	74%	86%	86%	76%
54.9%	62%	65%	62%	60%	54%	50%	60%	34%	56%	52%	54%	61%	54%	55%	61%	71%	45%	47%	55%	51%	43%
85.9%	92%	93%	90%	93%	87%	68%	79%	92%	89%	91%	82%	75%	90%	73%	88%	93%	90%	91%	86%	81%	81%
57.1%	60%	57%	57%	53%	76%	43%	60%	61%	72%	63%	52%	33%	62%	58%	75%	79%	29%	50%	34%	65%	61%
77.0%	83%	88%	80%	81%	82%	70%	82%	72%	74%	88%	77%	68%	82%	70%	82%	81%	68%	78%	71%	68%	73%
64.5%	57%	66%	68%	68%	65%	78%	63%	60%	63%	67%	71%	76%	61%	69%	59%	64%	68%	55%	74%	55%	48%
59.0%	56%	58%	58%	64%	49%	79%	52%	47%	51%	64%	72%	69%	61%	72%	60%	63%	53%	52%	77%	41%	40%
70.2%	63%	70%	63%	64%	80%	74%	68%	78%	63%	74%	70%	74%	82%	68%	64%	69%	77%	53%	75%	76%	70%
72.6%	77%	78%	82%	81%	77%	80%	70%	64%	71%	80%	77%	64%	64%	74%	73%	77%	72%	64%	71%	64%	64%
78.3%	79%	85%	86%	82%	85%	79%	87%	69%	79%	86%	86%	56%	82%	67%	85%	78%	72%	88%	72%	80%	62%
71.8%	66%	81%	69%	70%	69%	92%	72%	59%	67%	76%	83%	78%	69%	84%	69%	69%	69%	58%	72%	71%	65%
71.7%	74%	74%	78%	74%	73%	69%	77%	73%	68%	73%	71%	73%	69%	75%	78%	77%	67%	64%	74%	66%	58%
80.2%	80%	83%	85%	83%	87%	72%	77%	74%	78%	79%	79%	84%	85%	76%	78%	81%	80%	76%	83%	82%	82%
63.1%	72%	75%	73%	76%	63%	60%	71%	57%	63%	56%	63%	55%	54%	53%	71%	70%	63%	58%	61%	56%	56%
68.6%	76%	64%	73%	74%	66%	72%	75%	74%	63%	69%	67%	62%	64%	63%	72%	61%	65%	63%	68%	80%	69%
68.0%	74%	65%	68%	76%	65%	73%	60%	57%	65%	70%	72%	76%	63%	69%	76%	72%	60%	58%	77%	57%	74%
79.8%	76%	78%	71%	85%	85%	80%	78%	76%	85%	75%	72%	85%	85%	75%	85%	80%	78%	86%	83%	74%	84%
59.7%	64%	62%	68%	55%	55%	59%	61%	64%	55%	65%	67%	55%	55%	65%	55%	59%	62%	54%	57%		57%
74.9%	84%	75%	79%	84%	69%	67%	73%	77%	72%	77%	70%	68%	79%	67%	79%	82%	75%	77%	66%	68%	84%
78.9%	87%	76%	91%	91%	50%	80%	73%	83%	84%	73%	72%	72%	74%	72%	88%	89%	86%	87%	72%	78%	79%
74.0%	71%	76%	74%	70%	54%	89%	72%	69%	66%	68%	73%	84%	77%	84%	73%	65%	82%	68%	84%	83%	73%
75.7%	86%	75%	78%	78%	80%	80%	65%	55%	65%	78%	77%	83%	74%	77%	86%	84%	77%	55%	74%	71%	91%
78.9%	96%	76%	87%	84%	93%	86%	92%	79%	82%	92%	82%	62%	79%	74%	78%	81%	71%	63%	82%	63%	55%
77.4%	77%	86%	89%	88%	75%	89%	76%	67%	76%	76%	84%	77%	75%	88%	73%	90%	59%	61%	83%	70%	66%
95.8%	95%	96%	90%	97%	97%	99%	97%	95%	97%	93%	91%	97%	97%	93%	97%	99%	97%	95%	99%	92%	98%
79.0%	87%	86%	86%	85%	69%	83%	88%	88%	84%	88%	84%	58%	88%	80%	86%	87%	75%	35%	76%	77%	69%
83.9%	84%	84%	86%	86%	91%	77%	84%	86%	78%	89%	83%	85%	84%	96%	84%	84%	81%	81%	82%	81%	75%
90.7%	97%	94%	94%	95%	92%	89%	95%	65%	94%	89%	91%	94%	90%	95%	96%	95%	88%	83%	94%	82%	92%

Model Similarity Dendrogram

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