	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 62.6%	4th 62.1%	7th 61.3%	1st 63.2%	2nd 63.2%	16th 58.6%	13th 59.7%	6th 61.7%	12th 59.8%	15th 58.7%	9th 60.1%	20th 56.9%	10th 60.1%	11th 60.0%	8th 60.4%	5th 61.9%	17th 58.2%	21st 56.9%	19th 57.1%	14th 59.3%	18th 57.9%
63.1%	69%	67%	61%	70%	71%	50%	75%	66%	62%	67%	64%	64%	66%	59%	66%	70%	50%	66%	53%	43%	66%
52.5%	53%	49%	53%	58%	43%	55%	53%	50%	43%	56%	54%	56%	54%	56%	54%	51%	54%	50%	51%	51%	58%
48.2%	46%	46%	55%	46%	48%	55%	48%	47%	48%	47%	50%	51%	44%	51%	46%	49%	51%	51%	46%	44%	44%
41.9%	35%	51%	37%	33%	47%	65%	36%	53%	50%	25%	54%	53%	38%	69%	25%	28%	31%	47%	56%	29%	18%
78.5%	77%	75%	78%	77%	83%	75%	75%	80%	81%	80%	77%	72%	83%	83%	71%	84%	75%	88%	72%	88%	75%
81.1%	72%	74%	72%	72%	75%	94%	75%	94%	81%	92%	82%	76%	89%	84%	72%	81%	76%	72%	86%	97%	87%
56.3%	60%	58%	65%	65%	65%	63%	58%	57%	55%	52%	49%	47%	58%	58%	57%	61%	55%	53%	43%	56%	48%
42.4%	53%	42%	41%	52%	48%	29%	40%	51%	48%	43%	37%	48%	40%	44%	44%	44%	33%	46%	30%	44%	33%
62.9%	64%	58%	52%	58%	69%	48%	59%	77%	62%	52%	60%	70%	61%	75%	66%	71%	70%	54%	57%	80%	58%
52.2%	56%	63%	49%	51%	63%	51%	56%	59%	55%	39%	63%	38%	53%	61%	43%	50%	47%	53%	53%	57%	37%
58.7%	61%	60%	62%	64%	59%	64%	58%	64%	59%	60%	58%	44%	58%	58%	63%	62%	59%	36%	58%	62%	64%
40.4%	42%	51%	34%	39%	51%	47%	36%	53%	35%	24%	50%	48%	43%	48%	37%	32%	38%	29%	51%	31%	30%
66.5%	71%	66%	71%	72%	74%	70%	67%	67%	67%	64%	64%	50%	60%	60%	69%	70%	63%	64%	70%	65%	72%
58.5%	61%	58%	62%	60%	59%	63%	56%	55%	60%	56%	58%	59%	57%	57%	57%	59%	60%	52%	58%	60%	61%
60.2%	68%	64%	64%	66%	66%	58%	48%	55%	49%	66%	58%	40%	58%	57%	70%	64%	58%	49%	70%	70%	67%
63.4%	64%	68%	66%	73%	64%	67%	75%	66%	61%	67%	64%	59%	63%	59%	64%	62%	59%	64%	53%	59%	54%
72.8%	79%	82%	82%	82%	84%	74%	64%	62%	70%	68%	70%	74%	60%	70%	80%	84%	66%	70%	58%	68%	82%
54.4%	52%	59%	50%	58%	64%	49%	56%	64%	51%	53%	54%	58%	55%	45%	47%	54%	43%	58%	54%	70%	48%
62.7%	74%	60%	60%	70%	57%	45%	69%	70%	62%	48%	62%	56%	62%	56%	63%	68%	70%	66%	61%	76%	61%
51.9%	52%	51%	54%	55%	58%	58%	53%	57%	52%	52%	50%	49%	52%	49%	48%	49%	50%	49%	50%	50%	51%
48.1%	51%	54%	51%	51%	53%	41%	53%	53%	53%	47%	43%	52%	51%	43%	51%	49%	40%	52%	39%	38%	45%
65.0%	70%	67%	66%	69%	63%	70%	67%	72%	63%	64%	62%	54%	63%	62%	67%	65%	63%	62%	64%	65%	67%
68.0%	75%	66%	70%	68%	75%	63%	71%	65%	65%	68%	70%	62%	66%	67%	75%	71%	67%	67%	67%	67%	63%
64.5%	72%	68%	72%	70%	64%	65%	66%	56%	68%	62%	62%	53%	66%	64%	67%	65%	67%	57%	62%	62%	66%
56.1%	58%	51%	58%	63%	63%	64%	52%	57%	63%	58%	57%	58%	57%	54%	57%	64%	54%	38%	49%	51%	52%
54.8%	58%	54%	58%	62%	55%	46%	54%	55%	54%	55%	56%	58%	59%	53%	59%	59%	53%	50%	54%	49%	50%
54.4%	60%	58%	58%	65%	55%	42%	59%	64%	55%	57%	44%	58%	54%	45%	55%	60%	47%	54%	49%	49%	55%
63.2%	62%	67%	67%	70%	83%	52%	71%	68%	69%	56%	53%	59%	63%	53%	67%	71%	63%	54%	47%	64%	68%
41.0%	48%	62%	47%	51%	48%	31%	42%	36%	32%	29%	48%	31%	36%	43%	35%	42%	43%	43%	38%	50%	25%
53.2%	50%	50%	45%	59%	54%	45%	42%	57%	58%	53%	64%	49%	51%	49%	49%	52%	65%	60%	64%	52%	50%
60.4%	69%	66%	66%	63%	66%	61%	53%	54%	50%	66%	61%	45%	61%	61%	64%	66%	58%	47%	60%	66%	66%
90.0%	91%	93%	82%	94%	91%	82%	91%	91%	91%	92%	88%	87%	95%	87%	95%	85%	91%	87%	93%	95%	90%
48.2%	45%	46%	55%	46%	48%	55%	48%	47%	48%	47%	50%	51%	44%	51%	44%	53%	48%	51%	46%	44%	46%
64.3%	66%	67%	69%	62%	57%	69%	65%	64%	62%	66%	66%	57%	64%	64%	69%	66%	64%	65%	57%	64%	68%
50.2%	58%	55%	52%	52%	35%	43%	42%	49%	47%	44%	55%	52%	60%	55%	46%	52%	50%	55%	62%	44%	46%
70.8%	76%	71%	73%	78%	76%	67%	73%	68%	70%	77%	72%	64%	72%	64%	73%	73%	66%	68%	63%	69%	74%
76.8%	84%	86%	82%	81%	82%	79%	67%	68%	69%	83%	76%	58%	76%	74%	88%	80%	82%	75%	74%	68%	81%
87.2%	89%	93%	94%	90%	88%	90%	90%	83%	92%	87%	88%	81%	95%	83%	92%	89%	81%	85%	83%	73%	85%
49.7%	56%	50%	51%	60%	51%	44%	56%	53%	51%	51%	42%	54%	51%	44%	50%	57%	51%	55%	39%	37%	40%
68.2%	65%	65%	75%	65%	67%	76%	67%	67%	67%	66%	70%	71%	63%	71%	71%	69%	71%	71%	65%	63%	67%
69.4%	69%	67%	71%	78%	80%	62%	80%	79%	80%	80%	67%	68%	71%	71%	75%	80%	58%	19%	58%	77%	68%
52.0%	57%	56%	51%	43%	55%	43%	53%	49%	58%	45%	58%	61%	58%	58%	44%	47%	58%	58%	44%	51%	44%
55.7%	54%	55%	57%	57%	60%	51%	50%	50%	57%	60%	56%	53%	55%	63%	62%	55%	56%	56%	50%	53%	59%

Model Similarity Dendrogram

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