	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	3rd 69.3%	2nd 69.5%	4th 69.3%	1st 70.4%	6th 68.1%	15th 64.5%	12th 66.5%	5th 68.2%	11th 66.8%	13th 66.0%	8th 67.5%	18th 63.0%	7th 67.8%	14th 65.5%	10th 67.0%	9th 67.1%	16th 64.3%	17th 63.2%	20th 62.4%	21st 62.0%	19th 62.8%
64.6%	68%	68%	68%	69%	61%	58%	63%	68%	63%	62%	68%	63%	65%	65%	68%	68%	57%	63%	60%	62%	69%
72.2%	80%	69%	77%	77%	58%	81%	79%	76%	63%	67%	75%	70%	77%	77%	78%	68%	75%	66%	65%	70%	69%
95.0%	87%	98%	95%	97%	100%	95%	95%	97%	90%	95%	98%	99%	95%	95%	97%	99%	97%	91%	97%	83%	95%
40.6%	49%	41%	41%	51%	51%	48%	39%	52%	44%	50%	47%	21%	50%	49%	30%	28%	25%	39%	48%	30%	20%
83.0%	83%	82%	86%	86%	90%	74%	82%	79%	89%	86%	83%	75%	89%	82%	79%	86%	82%	92%	79%	84%	76%
80.0%	90%	82%	88%	88%	88%	57%	82%	85%	83%	85%	78%	78%	81%	65%	85%	86%	79%	85%	67%	63%	84%
60.9%	61%	56%	63%	74%	76%	47%	58%	53%	58%	73%	62%	58%	62%	58%	70%	67%	55%	70%	51%	40%	67%
57.0%	65%	64%	61%	67%	58%	46%	59%	56%	57%	69%	49%	54%	56%	55%	66%	58%	58%	56%	38%	55%	49%
67.7%	60%	72%	69%	68%	67%	65%	77%	69%	61%	69%	70%	68%	65%	62%	66%	69%	70%	76%	71%	71%	57%
42.8%	53%	51%	39%	50%	53%	48%	42%	50%	47%	45%	49%	19%	47%	55%	49%	25%	38%	37%	53%	32%	16%
75.6%	82%	79%	80%	80%	76%	81%	77%	74%	77%	70%	77%	64%	77%	74%	80%	77%	84%	51%	79%	77%	71%
45.0%	57%	65%	40%	62%	56%	40%	39%	51%	49%	36%	56%	20%	50%	60%	47%	50%	32%	27%	46%	23%	40%
66.4%	58%	72%	74%	61%	58%	78%	57%	77%	65%	54%	68%	50%	61%	64%	66%	66%	72%	72%	76%	73%	73%
62.7%	63%	64%	69%	63%	67%	70%	63%	63%	65%	63%	68%	59%	65%	63%	59%	64%	64%	51%	56%	63%	54%
76.4%	78%	83%	83%	83%	88%	78%	80%	67%	81%	83%	69%	81%	83%	71%	67%	80%	64%	78%	53%	84%	71%
58.7%	62%	55%	64%	56%	40%	61%	63%	61%	60%	54%	60%	63%	59%	62%	58%	59%	63%	52%	59%		63%
74.6%	70%	79%	75%	90%	79%	65%	78%	75%	76%	75%	78%	68%	68%	76%	71%	81%	71%	65%	85%	75%	67%
36.3%	48%	37%	43%	49%	51%	17%	29%	41%	33%	37%	37%	37%	37%	27%	45%	39%	30%	32%	36%	28%	30%
58.6%	65%	55%	59%	59%	59%	39%	76%	57%	62%	70%	57%	62%	59%	48%	73%	68%	24%	59%	51%	67%	61%
82.5%	86%	89%	80%	78%	74%	85%	85%	87%	87%	78%	87%	83%	90%	90%	77%	79%	78%	66%	84%	85%	84%
62.9%	63%	70%	69%	72%	64%	57%	66%	64%	65%	62%	60%	62%	65%	54%	66%	66%	51%	62%	51%	68%	64%
81.8%	87%	90%	87%	84%	88%	61%	90%	86%	83%	83%	83%	88%	91%	80%	77%	83%	73%	84%	61%		76%
65.1%	69%	70%	69%	59%	72%	68%	59%	69%	62%	66%	69%	56%	64%	65%	69%	60%	67%	72%	65%	64%	54%
48.4%	53%	51%	52%	46%	45%	54%	46%	49%	45%	39%	54%	41%	45%	50%	54%	45%	49%	48%	50%	47%	54%
68.2%	69%	71%	67%	67%	70%	75%	68%	71%	69%	67%	69%	68%	65%	72%	62%	64%	64%	69%	67%	72%	66%
64.5%	59%	61%	69%	62%	44%	71%	56%	52%	64%	59%	74%	72%	60%	79%	62%	57%	78%	63%	82%	59%	72%
59.3%	59%	62%	64%	64%	61%	56%	59%	60%	59%	59%	57%	61%	55%	57%	61%	60%	57%	56%	54%	60%	64%
61.0%	56%	71%	53%	63%	68%	39%	54%	59%	71%	62%	64%	61%	64%	48%	61%	72%	59%	72%	49%	65%	69%
34.2%	34%	38%	36%	52%	37%		34%	49%	25%	27%	36%	18%	31%	35%	42%	38%	40%	32%	26%	34%	20%
59.3%	67%	58%	52%	73%	67%	52%	52%	56%	60%	68%	55%	50%	56%	56%	64%	63%	58%	63%	61%	56%	59%
77.2%	83%	85%	84%	72%	93%	82%	94%	87%	90%	61%	77%	84%	80%	77%	61%	71%	88%	58%	59%	65%	70%
67.8%	78%	63%	61%	62%	66%	61%	70%	68%	76%	61%	67%	65%	70%	70%	61%	63%	66%	74%	68%	83%	71%
56.4%	50%	61%	63%	62%	59%	63%	55%	56%	50%	63%	57%	59%	55%	55%	59%	58%	59%	51%	50%	44%	55%
75.0%	77%	78%	83%	59%	57%	83%	78%	83%	79%	65%	80%	76%	80%	81%	78%	73%	78%	80%	73%	63%	71%
74.3%	89%	79%	83%	83%	70%	62%	53%	74%	75%	72%	76%	71%	91%	74%	70%	86%	80%	60%	83%	73%	57%
74.0%	74%	80%	79%	74%	70%	79%	76%	81%	70%	75%	73%	73%	73%	72%	72%	75%	73%	71%	68%	74%	72%
57.0%	65%	57%	60%	60%	58%	66%	65%	59%	60%	56%	57%	56%	58%	55%	45%	57%	58%	45%	55%	53%	52%
84.1%	82%	84%	88%	87%	90%	90%	93%	89%	87%	88%	78%	75%	92%	75%	88%	86%	79%	78%	74%	76%	88%
70.1%	84%	79%	68%	84%	82%	57%	74%	67%	69%	81%	70%	73%	80%	58%	85%	80%	59%	59%	42%	54%	68%
94.9%	87%	98%	95%	97%	100%	95%	95%	97%	90%	95%	98%	99%	95%	95%	97%	99%	100%	91%	97%	83%	90%
59.6%	67%	60%	69%	69%	61%	63%	58%	62%	57%	62%	63%	57%	56%	56%	67%	58%	60%	52%	45%	54%	55%
84.4%	84%	84%	100%	95%	81%	84%	86%	83%	84%	85%	77%	92%	86%	86%	71%	80%	82%	86%	93%	74%	80%
68.4%	80%	76%	74%	74%	77%	57%	55%	74%	74%	61%	74%	62%	69%	69%	78%	76%	69%	65%	57%	58%	58%

Model Similarity Dendrogram

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