	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 64.5%	5th 63.4%	7th 62.5%	3rd 64.0%	2nd 64.1%	15th 60.2%	12th 60.7%	4th 63.5%	14th 60.3%	11th 61.0%	9th 61.9%	20th 58.3%	10th 61.7%	16th 59.6%	8th 62.0%	6th 63.1%	13th 60.6%	19th 58.9%	18th 59.4%	21st 58.0%	17th 59.5%
59.0%	65%	59%	61%	63%	60%	48%	56%	59%	56%	59%	59%	60%	58%	59%	67%	63%	59%	59%	59%	51%	59%
38.5%	42%	33%	36%	38%	38%	30%	28%	31%	25%	39%	48%	47%	38%	47%	45%	32%	54%	38%	40%	42%	37%
82.5%	78%	77%	88%	86%	79%	88%	85%	84%	79%	85%	85%	92%	75%	86%	84%	78%	84%	84%	79%	75%	82%
53.9%	56%	57%	47%	45%	63%	59%	55%	59%	54%	50%	63%	59%	65%	66%	46%	43%	46%	59%	66%	43%	31%
84.3%	90%	81%	91%	91%	84%	77%	99%	90%	88%	79%	81%	83%	77%	77%	88%	79%	81%	81%	79%	76%	98%
81.3%	77%	81%	73%	78%	87%	92%	82%	86%	87%	86%	82%	81%	87%	70%	74%	82%	81%	75%	85%	75%	86%
59.1%	61%	59%	58%	57%	56%	58%	57%	61%	58%	59%	64%	57%	59%	56%	60%	61%	57%	66%	59%	55%	63%
52.1%	60%	49%	53%	67%	54%	53%	49%	57%	56%	56%	44%	55%	53%	47%	52%	60%	58%	48%	33%	45%	45%
68.1%	69%	68%	61%	68%	68%	64%	68%	77%	68%	71%	63%	73%	68%	57%	64%	68%	73%	76%	66%	77%	63%
27.8%	28%	32%	17%	30%	32%	33%	37%	29%	26%	25%	25%	25%	36%	38%	21%	32%	23%	38%	25%	25%	7%
62.0%	66%	67%	64%	69%	54%	64%	64%	69%	54%	55%	64%	49%	64%	49%	69%	74%	59%	45%	64%	64%	74%
29.1%	33%	44%	20%	24%	41%	30%	30%	34%	30%	23%	36%	29%	29%	43%	21%	34%	17%	29%	29%	17%	19%
79.2%	81%	82%	83%	85%	78%	82%	73%	82%	73%	77%	80%	75%	71%	80%	83%	80%	82%	76%	80%	79%	82%
52.3%	53%	53%	54%	55%	55%	58%	53%	56%	50%	56%	51%	50%	54%	50%	50%	55%	50%	49%	46%	48%	52%
45.8%	47%	48%	49%	47%	57%	47%	45%	48%	42%	46%	42%	29%	43%	42%	48%	47%	42%	51%	50%	39%	52%
48.7%	51%	53%	59%	56%	47%	53%	57%	57%	48%	47%	51%	47%	50%	44%	48%	51%	36%	41%	36%	47%	43%
54.8%	62%	63%	66%	66%	52%	43%	48%	51%	55%	47%	45%	41%	46%	55%	67%	62%	55%	50%	58%	58%	61%
58.6%	61%	64%	69%	65%	58%	57%	63%	67%	56%	59%	58%	47%	57%	50%	62%	64%	43%	64%	54%	56%	57%
51.7%	55%	55%	57%	57%	48%	31%	61%	49%	52%	51%	57%	47%	61%	47%	54%	59%	48%	39%	43%	63%	51%
64.0%	70%	64%	70%	70%	65%	67%	63%	60%	59%	59%	63%	67%	71%	63%	62%	63%	60%	52%	67%	63%	66%
85.1%	78%	81%	85%	83%	89%	88%	83%	81%	85%	88%	94%	76%	89%	94%	79%	86%	86%	84%	87%	84%	87%
68.8%	72%	74%	69%	73%	69%	71%	73%	73%	67%	72%	70%	60%	68%	70%	71%	72%	63%	65%	66%	75%	52%
53.0%	58%	56%	57%	55%	59%	54%	49%	52%	50%	51%	54%	43%	50%	57%	53%	51%	55%	60%	54%	44%	52%
65.1%	73%	70%	66%	63%	72%	62%	65%	71%	63%	63%	70%	46%	63%	63%	69%	67%	66%	54%	70%	62%	70%
51.3%	51%	47%	57%	51%	57%	56%	48%	51%	50%	53%	43%	57%	51%	49%	45%	55%	56%	44%	57%	47%	53%
57.5%	63%	60%	60%	68%	63%	48%	59%	60%	60%	56%	55%	59%	59%	52%	61%	58%	49%	55%	54%	49%	60%
54.9%	60%	59%	55%	67%	64%	43%	56%	59%	62%	59%	51%	69%	60%	45%	56%	53%	55%	60%	61%	10%	49%
55.8%	61%	57%	60%	66%	63%	54%	59%	68%	55%	62%	44%	58%	55%	47%	55%	60%	58%	43%	44%	48%	54%
38.2%	40%	50%	36%	50%	37%	27%	35%	34%	34%	29%	49%	32%	40%	40%	48%	47%	40%	42%	32%	40%	20%
64.3%	62%	62%	62%	68%	78%	61%	54%	58%	68%	61%	70%	67%	57%	63%	67%	65%	80%	57%	68%	63%	59%
70.5%	71%	77%	73%	76%	73%	76%	62%	72%	69%	71%	70%	66%	70%	70%	66%	74%	73%	63%	70%	66%	72%
78.8%	84%	84%	73%	83%	81%	73%	75%	77%	81%	75%	75%	68%	86%	75%	77%	80%	77%	77%	81%	86%	86%
69.9%	67%	65%	75%	65%	67%	76%	73%	71%	67%	73%	73%	80%	63%	73%	71%	67%	71%	71%	67%	63%	69%
65.0%	69%	65%	68%	63%	67%	71%	65%	66%	63%	64%	66%	53%	69%	53%	69%	69%	67%	63%	55%	73%	66%
56.9%	69%	61%	69%	59%	51%	46%	44%	52%	54%	57%	60%	49%	66%	58%	60%	59%	47%	60%	60%	68%	46%
60.5%	64%	61%	66%	57%	66%	67%	64%	67%	55%	60%	62%	58%	58%	57%	55%	59%	62%	52%	57%	61%	63%
72.0%	80%	79%	80%	70%	81%	67%	57%	80%	69%	78%	71%	51%	71%	72%	77%	79%	80%	50%	71%	72%	78%
82.2%	85%	80%	84%	78%	91%	90%	86%	89%	87%	92%	84%	68%	85%	70%	87%	84%	78%	80%	67%	70%	92%
48.4%	47%	47%	45%	55%	49%	49%	56%	58%	51%	52%	44%	52%	52%	43%	48%	53%	47%	49%	39%	43%	38%
95.1%	97%	97%	92%	94%	99%	92%	94%	96%	99%	94%	94%	87%	95%	94%	95%	94%	96%	96%	99%	95%	98%
52.5%	58%	55%	49%	58%	55%	52%	54%	59%	54%	57%	55%	49%	53%	43%	53%	54%	45%	56%	45%	50%	48%
72.5%	78%	72%	68%	69%	76%	60%	69%	74%	70%	67%	78%	83%	77%	78%	68%	71%	83%	74%	76%	70%	61%
64.9%	80%	77%	62%	62%	75%	71%	55%	55%	64%	59%	70%	64%	55%	70%	73%	69%	64%	58%	55%		59%

Model Similarity Dendrogram

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