	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	1st 68.0%	3rd 67.2%	2nd 67.3%	8th 64.7%	16th 62.1%	12th 63.3%	10th 63.8%	17th 61.9%	19th 60.7%	9th 64.4%	6th 65.3%	21st 56.7%	5th 65.5%	13th 63.1%	4th 65.8%	7th 65.3%	15th 62.2%	20th 58.3%	11th 63.8%	18th 61.0%	14th 63.0%
57.6%	67%	62%	64%	61%	38%	53%	56%	62%	54%	66%	57%	59%	61%	58%	59%	61%	44%	56%	57%	57%	58%
38.5%	32%	34%	36%	36%	33%	41%	24%	29%	20%	23%	40%	34%	33%	47%	30%	41%	71%	67%	47%	58%	33%
91.4%	92%	95%	97%	95%	75%	97%	84%	94%	84%	98%	97%	92%	92%	92%	92%	91%	92%	98%	84%	86%	92%
61.9%	73%	64%	55%	55%	73%	71%	56%	64%	63%	55%	55%	55%	55%	62%	71%	74%	54%	65%	69%	55%	55%
78.6%	85%	79%	92%	87%	74%	86%	85%	70%	81%	67%	64%	66%	77%	67%	81%	85%	76%	66%	81%	100%	81%
78.2%	74%	72%	71%	74%	75%	86%	89%	84%	80%	76%	74%	77%	86%	86%	74%	74%	86%	81%	80%	75%	68%
51.4%	54%	61%	58%	38%	53%	52%	55%	54%	54%	49%	57%	58%	50%	53%	53%	47%	51%	42%	57%	40%	43%
59.5%	71%	62%	71%	66%	63%	45%	71%	64%	51%	77%	63%	59%	58%	58%	69%	52%	52%	46%	53%	43%	55%
64.3%	64%	60%	68%	68%	68%	51%	69%	68%	70%	64%	62%	61%	67%	56%	61%	64%	62%	66%	67%	67%	67%
52.4%	64%	53%	46%	65%	49%	65%	49%	46%	51%	51%	55%	55%	51%	55%	55%	54%	43%	45%	51%	47%	51%
49.3%	59%	60%	64%	38%	0%	64%	49%	49%	41%	24%	49%	38%	49%	59%	45%	47%	69%	34%	69%	64%	64%
72.6%	78%	72%	70%	70%	70%	71%	75%	71%	69%	90%	75%	80%	75%	70%	70%	67%	71%	70%	75%	56%	80%
76.2%	78%	83%	80%	80%	83%	85%	70%	61%	71%	85%	80%	54%	78%	80%	73%	81%	82%	70%	82%	55%	90%
54.4%	58%	56%	51%	47%	58%	61%	58%	58%	50%	52%	55%	55%	58%	55%	59%	59%	47%	47%	55%	54%	49%
46.6%	55%	48%	44%	46%	57%	49%	40%	33%	36%	50%	51%	29%	47%	45%	51%	50%	51%	51%	42%	53%	50%
53.2%	58%	55%	63%	57%	51%	44%	58%	59%	55%	57%	58%	47%	51%	51%	60%	52%	53%	44%	51%	36%	58%
62.3%	77%	74%	77%	66%	64%	52%	58%	45%	60%	64%	64%	35%	58%	55%	71%	73%	52%	52%	61%	75%	75%
62.0%	67%	62%	71%	61%	67%	50%	61%	61%	56%	67%	54%	58%	75%	58%	68%	62%	61%	43%	68%	64%	67%
42.2%	46%	30%	46%	50%	59%	39%	58%	46%	35%	52%	46%	25%	35%	30%	47%	53%	37%	33%	37%	33%	50%
63.2%	67%	69%	73%	67%	51%	73%	63%	56%	51%	50%	70%	67%	74%	65%	66%	67%	47%	69%	60%	67%	56%
71.3%	63%	80%	80%	67%	81%	89%	74%	60%	76%	56%	86%	73%	74%	94%	58%	64%	66%	56%	75%	72%	53%
67.5%	68%	73%	71%	67%	70%	71%	74%	69%	65%	70%	64%	63%	73%	70%	65%	73%	68%	64%	68%	70%	41%
47.0%	45%	45%	44%	44%	58%	57%	57%	49%	52%	45%	60%	37%	44%	50%	46%	44%	43%	36%	50%	44%	37%
57.1%	77%	72%	61%	54%	54%	67%	55%	52%	57%	77%	71%	7%	64%	62%	72%	64%	63%	40%	73%	30%	28%
50.1%	56%	56%	48%	40%	54%	60%	56%	47%	39%	51%	56%	47%	58%	54%	54%	59%	39%	40%	54%	34%	51%
60.1%	64%	61%	75%	61%	55%	53%	59%	57%	54%	61%	61%	59%	64%	61%	61%	63%	58%	55%	59%	59%	62%
68.1%	79%	71%	71%	71%	67%	41%	55%	75%	75%	86%	47%	69%	67%	54%	73%	70%	83%	65%	59%	70%	82%
60.0%	66%	64%	65%	65%	57%	60%	67%	71%	55%	75%	63%	61%	63%	54%	65%	55%	40%	41%	47%	70%	55%
61.7%	73%	86%	71%	86%	67%	49%	64%	46%	70%	46%	64%	47%	46%	51%	66%	67%	43%	53%	64%	79%	57%
77.4%	70%	80%	75%	69%	71%	59%	73%	79%	82%	84%	82%	74%	86%	80%	81%	79%	79%	81%	80%	75%	86%
70.3%	77%	79%	74%	74%	60%	73%	70%	70%	63%	80%	68%	62%	69%	70%	71%	73%	73%	73%	63%	66%	69%
67.9%	64%	66%	64%	66%	86%	64%	77%	56%	77%	59%	64%	68%	68%	68%	61%	68%	68%	68%	77%	68%	68%
82.1%	84%	82%	84%	82%	63%	84%	71%	93%	71%	90%	84%	80%	80%	80%	80%	79%	80%	90%	71%	98%	98%
66.4%	67%	69%	68%	61%	67%	74%	75%	71%	64%	64%	70%	67%	63%	65%	72%	70%	66%	65%	60%	54%	62%
62.4%	77%	67%	64%	68%	40%	67%	41%	75%	64%	60%	75%	40%	71%	58%	73%	70%	66%	54%	58%	69%	54%
61.0%	60%	65%	67%	62%	58%	60%	64%	61%	52%	60%	66%	61%	67%	63%	57%	59%	63%	62%	58%	62%	55%
71.2%	83%	79%	67%	70%	86%	67%	57%	54%	60%	72%	79%	53%	68%	71%	74%	76%	80%	75%	69%	65%	90%
76.8%	84%	80%	91%	84%	97%	81%	87%	84%	84%	76%	80%	54%	90%	70%	84%	71%	57%	47%	77%	47%	87%
53.1%	54%	60%	59%	62%	59%	55%	59%	54%	57%	52%	49%	54%	59%	44%	55%	52%	49%	47%	39%	52%	45%
85.0%	87%	85%	83%	85%	95%	83%	96%	74%	96%	78%	83%	87%	87%	87%	80%	84%	87%	78%	96%	66%	87%
51.5%	55%	53%	55%	55%	39%	59%	53%	54%	51%	63%	53%	53%	55%	50%	58%	55%	53%	12%	51%	50%	55%
81.0%	87%	89%	83%	88%	76%	65%	78%	94%	64%	86%	81%	44%	94%	81%	94%	88%	91%	82%	86%	75%	74%
65.4%	63%	76%	77%	75%	48%	50%	53%	43%	49%	63%	77%	73%	75%	75%	74%	69%	60%	77%	62%	64%	70%

Model Similarity Dendrogram

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