	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	4th 70.3%	6th 70.2%	2nd 72.1%	1st 72.2%	3rd 70.4%	17th 65.3%	10th 68.7%	8th 69.6%	9th 68.7%	11th 68.4%	5th 70.2%	13th 66.7%	12th 68.3%	14th 66.3%	20th 64.4%	7th 70.0%	19th 64.9%	18th 65.3%	16th 65.9%	15th 66.2%	21st 63.4%
67.1%	69%	68%	72%	77%	70%	59%	64%	73%	68%	67%	68%	65%	68%	65%	68%	68%	63%	66%	61%	63%	67%
73.5%	84%	71%	77%	82%	53%	76%	79%	76%	63%	70%	77%	75%	77%	70%	75%	66%	63%		78%	75%	84%
90.1%	90%	90%	95%	95%	95%	97%	90%	95%	83%	97%	93%	90%	83%	91%	91%	91%	91%	87%	90%	83%	76%
84.6%	90%	85%	90%	90%	73%	87%	70%	78%	78%	86%	90%	91%	90%	78%	76%	91%	77%	84%	92%	90%	91%
85.5%	86%	83%	81%	81%	89%	81%	86%	86%	94%	86%	86%	89%	86%	89%	77%	80%	84%	84%	89%	89%	89%
82.0%	85%	90%	90%	90%	98%	82%	78%	90%	78%	85%	85%	71%	78%	79%	82%	90%	75%	81%	82%	82%	50%
54.4%	51%	46%	54%	69%	62%	53%	54%	65%	47%	60%	46%	58%	58%	45%	51%	51%	52%	62%	47%	67%	44%
60.3%	67%	65%	61%	74%	59%	49%	65%	66%	60%	75%	67%	58%	67%	58%	58%	63%	53%	46%	41%	56%	58%
70.1%	58%	62%	63%	69%	71%	61%	69%	78%	71%	69%	69%	78%	69%	70%	58%	69%	71%	75%	71%	86%	86%
79.4%	76%	81%	72%	86%	91%	84%	76%	73%	76%	78%	92%	91%	72%	77%	68%	82%	60%	72%	86%	83%	91%
71.7%	78%	73%	79%	78%	59%	88%	68%	73%	74%	53%	78%	63%	53%	67%	78%	66%	61%	53%	88%	95%	81%
78.6%	85%	90%	85%	85%	79%	76%	69%	77%	77%	70%	85%	79%	73%	77%	85%	91%	50%	68%	92%	79%	79%
67.2%	54%	76%	76%	62%	71%	80%	66%	62%	72%	59%	84%	50%	66%	74%	59%	69%	71%	63%	78%	72%	48%
69.4%	70%	69%	69%	67%	75%	72%	70%	67%	70%	75%	72%	75%	70%	68%	64%	67%	62%	74%	63%	69%	70%
74.4%	91%	67%	90%	87%	85%	61%	87%	88%	84%	77%	76%	90%	77%	74%	0%	77%	70%	79%	67%	76%	59%
64.4%	64%	66%	68%	57%	57%	65%	68%	64%	67%	72%	67%	58%	61%	65%	68%	69%	65%		62%	57%	68%
79.6%	75%	79%	75%	90%	94%	68%	75%	78%	79%	79%	79%	83%	79%	80%	82%	81%	65%	70%	93%	81%	87%
34.7%	48%	37%	37%	49%	37%	21%	29%	45%	37%	44%	28%	26%	36%	32%	29%	40%	27%	42%	28%	28%	29%
34.2%	40%	27%	43%	28%	56%	26%	27%	42%	41%	26%	26%	6%	42%	29%	48%	60%	40%	38%	18%	27%	29%
78.1%	80%	88%	80%	80%	82%	79%	85%	71%	85%	76%	82%	78%	85%	86%	76%	84%	81%	79%	74%	55%	55%
65.9%	71%	72%	69%	72%	69%	60%	69%	62%	66%	69%	59%	69%	69%	61%	71%	59%	66%	57%	53%	60%	80%
79.0%	87%	84%	71%	85%	86%	61%	83%	87%	83%	83%	61%	88%	83%	81%	78%	90%	72%	80%	61%	70%	84%
47.0%	38%	45%	50%	50%	63%	66%	56%	44%	28%	44%	62%	22%	66%	55%	44%	44%	40%	49%	44%	56%	22%
49.4%	51%	53%	59%	53%	51%	54%	44%	43%	51%	48%	56%	26%	51%	50%	50%	51%	51%		51%	51%	44%
66.5%	64%	67%	70%	65%	68%	65%	68%	66%	68%	65%	72%	61%	61%	72%	65%	68%	65%	74%	68%	60%	65%
71.5%	69%	85%	69%	59%	69%	77%	67%	53%	72%	69%	85%	72%	69%	79%	74%	76%	72%	71%	85%	67%	63%
61.9%	64%	63%	67%	67%	58%	46%	57%	61%	59%	67%	60%	60%	58%	61%	63%	66%	57%	63%	67%	72%	63%
56.0%	56%	61%	53%	61%	62%	34%	61%	59%	70%	56%	52%	51%	60%	50%	67%	63%	57%	64%	50%	59%	29%
39.9%	52%	51%	52%	52%	50%	34%	52%	33%	30%	30%	45%	38%	30%	38%	38%	45%	30%	22%	45%	38%	33%
57.5%	70%	58%	70%	70%	47%	50%	65%	57%	54%	62%	55%	68%	50%	52%	56%	55%	48%	58%	52%	52%	59%
82.3%	90%	92%	100%	100%	84%	62%	90%	100%	88%	75%	83%	88%	84%	80%	52%	84%	90%	75%	71%	79%	61%
74.0%	76%	76%	61%	61%	61%	68%	76%	61%	83%	68%	72%	76%	83%	74%	76%	76%	90%	87%	76%	68%	86%
50.7%	50%	50%	63%	63%	63%	56%	50%	63%	50%	56%	53%	50%	44%	51%	41%	50%	50%	44%	50%	26%	41%
78.3%	83%	83%	88%	65%	70%	88%	86%	86%	75%	72%	86%	83%	83%	74%	65%	80%	80%	89%	71%	65%	72%
69.2%	58%	83%	74%	68%	75%	69%	75%	91%	91%	75%	71%	68%	68%	58%	75%	75%	79%	51%	44%	56%	49%
73.4%	80%	81%	79%	80%	54%	71%	76%	81%	76%	77%	76%	74%	79%	73%	64%	65%	74%	64%	66%	73%	78%
58.2%	61%	65%	66%	69%	60%	58%	56%	57%	61%	61%	62%	58%	59%	62%	55%	51%	56%	55%	50%	55%	45%
85.8%	88%	87%	88%	88%	97%	79%	97%	88%	88%	88%	93%	77%	84%	76%	88%	78%	84%	81%	85%	86%	82%
72.7%	84%	70%	68%	84%	74%	53%	77%	74%	77%	71%	74%	75%	77%	65%	84%	79%	74%	65%	58%	69%	75%
90.7%	90%	90%	95%	95%	95%	97%	90%	95%	83%	97%	93%	90%	83%	91%	83%	97%	91%	83%	90%	97%	79%
61.9%	72%	60%	72%	72%	69%	60%	59%	58%	60%	67%	69%	71%	67%	53%	66%	66%	62%	17%	56%	56%	67%
75.7%	72%	65%	85%	67%	92%	84%	85%	85%	91%	81%	62%	68%	85%	54%	67%	77%	69%	86%	85%	67%	62%
55.6%	55%	65%	74%	63%	55%	49%	39%	40%	47%	55%	69%	61%	53%	68%	55%	60%	53%	52%	57%	53%	45%

Model Similarity Dendrogram

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