	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 69.7%	7th 68.6%	3rd 69.5%	1st 69.8%	5th 69.1%	21st 61.6%	12th 67.0%	8th 68.0%	10th 67.8%	9th 68.0%	6th 69.0%	19th 65.1%	12th 67.0%	14th 66.5%	4th 69.3%	11th 67.7%	15th 66.2%	18th 65.3%	17th 65.4%	20th 64.7%	16th 66.0%
62.7%	66%	63%	67%	65%	69%	47%	72%	72%	66%	67%	66%	60%	60%	62%	69%	68%	54%	53%	54%	54%	62%
67.2%	62%	67%	67%	69%	52%	66%	59%	69%	57%	59%	71%	73%	70%	71%	69%	62%	82%	69%	76%	71%	70%
68.0%	63%	67%	69%	75%	73%	81%	67%	67%	62%	72%	72%	77%	67%	67%	71%	67%	67%	65%	59%	57%	63%
55.7%	59%	54%	45%	56%	64%	49%	59%	63%	65%	60%	65%	58%	60%	64%	50%	49%	43%	46%	65%	55%	40%
81.8%	74%	82%	81%	78%	93%	88%	75%	78%	81%	88%	76%	77%	91%	83%	82%	78%	88%	80%	83%	85%	76%
88.5%	92%	94%	84%	84%	87%	61%	92%	93%	99%	89%	93%	92%	92%	90%	82%	89%	94%	87%	87%	81%	97%
72.3%	75%	70%	73%	76%	76%	65%	74%	74%	74%	76%	73%	74%	71%	62%	73%	77%	73%	66%	65%	77%	74%
78.0%	88%	74%	76%	85%	82%	54%	73%	82%	83%	87%	81%	86%	81%	73%	88%	88%	69%	79%	70%	70%	69%
89.7%	89%	89%	92%	87%	91%	87%	92%	84%	95%	89%	92%	86%	89%	86%	82%	80%	87%	98%	94%	96%	98%
42.1%	47%	45%	33%	53%	46%	50%	33%	50%	44%	41%	61%	35%	46%	58%	30%	31%	34%	47%	54%	26%	20%
70.0%	79%	66%	80%	80%	54%	80%	75%	72%	69%	80%	67%	67%	62%	62%	79%	76%	52%	44%	72%	74%	81%
40.4%	50%	49%	37%	48%	56%	38%	38%	50%	41%	39%	48%	47%	35%	45%	38%	37%	27%	25%	48%	34%	18%
77.3%	76%	82%	83%	83%	75%	79%	74%	86%	76%	74%	79%	70%	73%	73%	78%	78%	76%	73%	78%	74%	84%
64.8%	65%	66%	74%	51%	59%	75%	68%	58%	58%	51%	74%	73%	68%	73%	75%	69%	61%	57%	64%	52%	70%
73.3%	83%	75%	78%	78%	68%	83%	69%	68%	66%	74%	81%	52%	69%	69%	80%	79%	75%	67%	73%	70%	82%
73.0%	77%	77%	82%	84%	80%	51%	80%	78%	72%	79%	76%	73%	73%	68%	77%	79%	62%	66%	59%	70%	69%
66.0%	68%	80%	70%	81%	94%	53%	62%	55%	70%	69%	65%	53%	65%	58%	83%	67%	65%	43%	54%	62%	68%
44.1%	49%	45%	54%	61%	54%	19%	42%	50%	44%	46%	38%	45%	40%	31%	48%	46%	33%	61%	36%	37%	48%
70.0%	62%	65%	73%	63%	86%	35%	80%	69%	80%	76%	56%	44%	75%	61%	88%	85%	78%	81%	50%	81%	81%
67.4%	71%	58%	65%	72%	78%	66%	73%	68%	68%	70%	66%	71%	67%	58%	74%	74%	62%	68%	60%	69%	57%
74.0%	74%	71%	82%	80%	80%	70%	80%	73%	80%	74%	77%	67%	73%	75%	66%	66%	70%	71%	70%	70%	85%
62.5%	64%	67%	59%	59%	59%	75%	61%	66%	63%	65%	74%	47%	62%	62%	44%	66%	67%	51%	77%	72%	53%
52.4%	57%	48%	52%	49%	48%	47%	59%	61%	55%	56%	52%	43%	49%	52%	54%	57%	50%	56%	56%	54%	45%
75.1%	79%	73%	82%	82%	87%	58%	88%	75%	76%	81%	74%	74%	78%	74%	76%	78%	68%	75%	61%	68%	71%
62.9%	57%	69%	71%	57%	59%	65%	66%	56%	56%	57%	71%	73%	64%	73%	59%	51%	55%	51%	61%	69%	80%
67.9%	67%	71%	76%	70%	70%	56%	73%	60%	73%	64%	73%	67%	64%	70%	72%	64%	66%	62%	66%	65%	77%
56.6%	60%	57%	62%	65%	63%	38%	55%	60%	60%	58%	53%	60%	58%	54%	61%	60%	52%	54%	52%	49%	57%
69.2%	67%	73%	76%	76%	74%	49%	74%	81%	70%	75%	62%	72%	72%	61%	78%	74%	74%	68%	56%		51%
51.3%	58%	60%	49%	57%	46%	34%	54%	57%	53%	47%	57%	42%	47%	56%	58%	62%	63%	65%	47%	40%	26%
49.5%	51%	44%	52%	56%	59%	37%	33%	55%	48%	48%	55%	69%	47%	46%	48%	50%	52%	55%	53%	37%	44%
60.5%	64%	63%	64%	54%	64%	63%	43%	54%	51%	53%	60%	59%	50%	60%	61%	55%	67%	72%	68%	65%	80%
59.7%	65%	61%	59%	57%	55%	47%	61%	61%	67%	56%	56%	51%	61%	61%	56%	56%	61%	63%	70%	70%	59%
68.3%	63%	67%	69%	71%	73%	81%	67%	67%	62%	72%	72%	77%	67%	67%	77%	72%	67%	65%	59%	57%	63%
73.7%	78%	72%	79%	79%	72%	61%	75%	72%	79%	79%	72%	69%	75%	67%	73%	74%	83%	74%	63%	74%	77%
59.9%	68%	63%	64%	63%	44%	61%	60%	56%	59%	67%	57%	59%	62%	65%	54%	52%	63%	67%	68%	60%	45%
60.7%	61%	68%	60%	55%	40%	77%	58%	61%	53%	52%	58%	65%	55%	65%	60%	55%	69%	70%	69%	55%	68%
70.3%	77%	75%	74%	66%	77%	86%	58%	54%	63%	67%	70%	48%	68%	70%	79%	69%	74%	72%	74%	68%	87%
89.0%	90%	93%	88%	96%	93%	92%	95%	83%	92%	89%	86%	82%	93%	80%	94%	93%	82%	86%	83%	90%	88%
59.8%	62%	64%	62%	62%	65%	61%	59%	58%	58%	51%	61%	52%	52%	61%	56%	49%	64%	67%	65%	61%	65%
95.3%	96%	100%	98%	91%	93%	85%	100%	100%	95%	94%	94%	89%	100%	100%	98%	94%	100%	98%	91%	89%	96%
75.8%	78%	80%	84%	78%	57%	63%	82%	82%	80%	80%	78%	78%	81%	83%	76%	80%	73%	44%	73%	80%	82%
55.6%	64%	52%	51%	50%	56%	42%	52%	58%		63%	63%	50%	59%	62%	63%	63%	63%	55%	51%	51%	45%
87.4%	100%	91%	91%	100%	100%	74%	72%	88%	86%	88%	94%	94%	91%	83%	100%	91%	81%	92%	77%	77%	65%

Model Similarity Dendrogram

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