	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	2nd 68.0%	8th 65.5%	6th 67.1%	1st 68.7%	4th 67.4%	21st 60.3%	12th 64.3%	3rd 67.6%	11th 64.7%	9th 65.3%	13th 64.3%	18th 61.4%	10th 65.0%	14th 63.3%	5th 67.3%	7th 66.5%	17th 61.4%	16th 61.9%	15th 62.4%	20th 60.3%	19th 60.7%
59.3%	69%	62%	63%	66%	60%	46%	50%	58%	59%	64%	64%	63%	60%	57%	60%	62%	55%	59%	53%	59%	56%
69.0%	66%	62%	76%	71%	54%	72%	63%	67%	61%	55%	77%	80%	77%	89%	67%	51%	80%	69%	77%	71%	64%
90.1%	85%	89%	100%	99%	95%	92%	98%	92%	85%	92%	94%	96%	86%	86%	92%	88%	92%	82%	85%	78%	87%
46.4%	48%	46%	46%	48%	57%	44%	51%	53%	52%	48%	57%	29%	46%	65%	33%	44%	39%	40%	57%	41%	30%
66.6%	67%	63%	71%	71%	68%	61%	81%	76%	70%	61%	67%	62%	61%	59%	71%	64%	61%	62%	61%	56%	85%
58.0%	63%	65%	68%	65%	70%	32%	61%	69%	62%	62%	49%	53%	63%	52%	60%	65%	56%	55%	52%	41%	55%
75.6%	81%	68%	69%	87%	86%	69%	68%	79%	71%	71%	72%	69%	74%	68%	87%	85%	73%	90%	73%	83%	64%
47.3%	58%	42%	52%	66%	54%	32%	44%	52%	50%	50%	41%	51%	46%	41%	46%	51%	41%	56%	41%	44%	35%
70.2%	68%	71%	61%	68%	78%	57%	61%	77%	65%	77%	65%	77%	76%	68%	73%	77%	76%	72%	59%	87%	62%
30.1%	31%	30%	30%	32%	38%	34%	26%	32%	38%	32%	30%	16%	33%	48%	29%	36%	24%	20%	38%	19%	16%
71.5%	70%	74%	84%	84%	69%	100%	82%	75%	67%	72%	60%	55%	69%	56%	82%	80%	43%	53%	60%	82%	85%
35.9%	37%	41%	36%	36%	45%	30%	29%	40%	41%	36%	45%	37%	39%	39%	34%	36%	30%	38%	38%	23%	23%
63.0%	60%	61%	67%	63%	61%	72%	57%	62%	58%	62%	68%	60%	57%	67%	64%	64%	69%	58%	67%	67%	60%
85.2%	89%	90%	69%	81%	79%	81%	84%	85%	93%	95%	91%	91%	84%	91%	86%	82%	90%	82%	95%	69%	82%
78.8%	79%	82%	84%	67%	84%	92%	74%	77%	81%	80%	81%	56%	78%	81%	79%	80%	76%	74%	88%	80%	82%
58.1%	64%	61%	66%	70%	58%	44%	61%	63%	57%	63%	55%	60%	57%	55%	67%	58%	54%	55%	46%	46%	60%
49.4%	56%	56%	56%	56%	59%	33%	43%	41%	50%	56%	43%	41%	41%	41%	66%	56%	37%	39%	56%	55%	56%
65.6%	70%	72%	74%	76%	71%	46%	61%	79%	65%	71%	72%	71%	66%	50%	76%	69%	51%	51%	58%	55%	73%
61.6%	68%	66%	70%	70%	41%	51%	66%	69%	63%	76%	62%	55%	63%	64%	53%	52%	67%	50%	71%	72%	44%
76.9%	87%	73%	62%	68%	94%	82%	78%	87%	78%	68%	78%	76%	78%	73%	74%	76%	91%	75%	72%	70%	74%
65.8%	64%	73%	74%	72%	69%	61%	68%	65%	69%	67%	67%	63%	69%	63%	61%	66%	61%	60%	58%	64%	67%
52.9%	60%	53%	52%	61%	52%	42%	58%	60%	54%	52%	45%	59%	58%	47%	62%	53%	47%	52%	44%	50%	50%
60.4%	68%	58%	67%	66%	77%	63%	60%	54%	60%	56%	67%	50%	60%	60%	67%	61%	58%	66%	58%	58%	34%
63.3%	63%	63%	56%	64%	52%	63%	63%	67%	61%	63%	66%	47%	64%	64%	66%	63%	69%	64%	76%	70%	65%
82.9%	79%	85%	74%	85%	87%	82%	86%	85%	86%	85%	80%	89%	89%	86%	85%	78%	86%	71%	79%	83%	80%
54.1%	64%	53%	55%	55%	57%	47%	49%	46%	52%	57%	54%	53%	54%	59%	59%	51%	54%	51%	58%	55%	53%
60.2%	72%	59%	71%	75%	66%	36%	62%	68%	63%	58%	44%	67%	67%	49%	68%	61%	47%	74%	54%	55%	49%
57.2%	64%	62%	67%	69%	58%	59%	64%	67%	59%	60%	48%	57%	58%	49%	67%	62%	46%	45%	49%	47%	44%
46.2%	49%	54%	59%	58%	48%	41%	51%	59%	41%	33%	57%	33%	47%	56%	46%	60%	25%	52%	45%	41%	15%
60.5%	71%	48%	58%	69%	85%	57%	54%	57%	63%	58%	58%	53%	55%	58%	67%	65%	66%	76%	56%	40%	56%
68.0%	71%	72%	80%	74%	77%	74%	73%	75%	68%	74%	58%	68%	68%	60%	69%	69%	56%	61%	60%	61%	61%
66.2%	71%	67%	57%	58%	61%	64%	58%	64%	71%	64%	63%	60%	70%	70%	78%	66%	61%	74%	71%	78%	65%
71.7%	65%	70%	81%	79%	76%	73%	79%	73%	66%	73%	74%	77%	67%	67%	73%	78%	73%	63%	66%	59%	74%
63.7%	68%	64%	68%	68%	76%	44%	65%	63%	63%	68%	53%	55%	63%	55%	74%	71%	63%	71%	57%	58%	70%
58.4%	63%	63%	52%	59%	48%	42%	47%	56%	58%	60%	60%	52%	67%	54%	68%	64%	65%	70%	65%	63%	50%
56.6%	60%	62%	66%	52%	55%	60%	66%	61%	55%	57%	60%	57%	55%	55%	48%	57%	53%	45%	46%	58%	61%
76.0%	81%	83%	77%	71%	79%	76%	74%	67%	75%	75%	81%	56%	75%	81%	77%	79%	81%	71%	81%	73%	84%
81.8%	94%	85%	89%	83%	73%	91%	88%	84%	86%	89%	74%	69%	85%	70%	94%	88%	74%	64%	71%	74%	93%
60.3%	67%	63%	64%	69%	67%	63%	70%	70%	62%	69%	54%	64%	64%	60%	63%	67%	52%	56%	55%	10%	57%
90.7%	85%	89%	100%	99%	95%	92%	98%	92%	85%	92%	94%	96%	86%	86%	92%	97%	92%	82%	85%	78%	89%
76.3%	77%	73%	69%	81%	78%	74%	79%	81%	76%	78%	77%	74%	81%	71%	77%	79%	61%	79%	72%	83%	82%
69.6%	78%	70%	65%	65%	72%	56%	58%	81%	66%	65%	81%	75%	74%	74%	59%	78%	76%	67%	68%	76%	57%
70.5%	75%	72%	79%	79%	70%	63%	59%	79%	79%	63%	79%	68%	66%	79%	76%	70%	70%	67%	63%	63%	62%

Model Similarity Dendrogram

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