	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	5th 72.3%	6th 72.1%	2nd 73.2%	1st 74.0%	17th 69.2%	19th 68.5%	11th 70.6%	15th 70.0%	14th 70.1%	9th 71.2%	4th 72.5%	7th 71.5%	10th 70.9%	8th 71.4%	13th 70.2%	12th 70.3%	18th 68.6%	16th 69.7%	3rd 72.9%	20th 68.5%	21st 68.1%
77.0%	82%	82%	82%	86%	78%	60%	75%	79%	76%	76%	76%	75%	78%	75%	81%	79%	79%	70%	82%	73%	72%
43.8%	44%	43%	46%	47%	25%	48%	36%	52%	39%	42%	57%	57%	52%	55%	39%	35%	46%	32%	53%	31%	41%
72.2%	76%	73%	82%	66%	66%	61%	76%	71%	71%	76%	82%	71%	71%	76%	66%	73%	71%	74%	71%	71%	73%
75.8%	80%	70%	77%	86%	72%	56%	80%	77%	79%	82%	79%	75%	80%	75%	76%	68%	67%	83%	77%	78%	75%
71.1%	64%	79%	64%	70%	79%	60%	76%	72%	67%	67%	76%	83%	72%	81%	76%	70%	76%	76%	64%	67%	54%
75.5%	68%	73%	61%	68%	73%	86%	72%	77%	77%	78%	73%	72%	78%	88%	72%	68%	77%	65%	89%	94%	77%
88.7%	93%	86%	89%	92%	90%	85%	90%	93%	93%	88%	90%	84%	90%	92%	81%	92%	72%	91%	95%	84%	93%
68.2%	74%	67%	67%	80%	64%	54%	74%	72%	66%	66%	62%	69%	72%	69%	76%	70%	71%	72%	62%		57%
83.0%	88%	83%	82%	82%	89%	62%	72%	78%	78%	83%	88%	83%	89%	84%	92%	93%	85%	89%	78%	82%	82%
73.8%	76%	70%	70%	76%	75%	75%	72%	75%	75%	78%	75%	75%	75%	75%	72%	71%	67%	72%	75%	75%	76%
51.1%	54%	54%	57%	57%	54%	57%	57%	60%	46%	52%	54%	46%	42%	44%	47%	56%	38%	43%	63%	34%	58%
68.1%	69%	62%	69%	69%	73%	58%	63%	73%	71%	76%	69%	65%	72%	65%	69%	70%	69%	70%	65%	64%	70%
61.0%	55%	69%	66%	66%	63%	70%	54%	59%	61%	62%	66%	50%	57%	60%	62%	62%	54%	59%	63%	62%	62%
71.3%	70%	65%	59%	70%	65%	74%	70%	71%	79%	73%	78%	82%	66%	75%	72%	70%	83%	63%	70%	78%	65%
82.9%	87%	82%	87%	87%	82%	79%	86%	81%	89%	84%	73%	82%	87%	87%	84%	84%	85%	78%	84%	76%	76%
72.6%	78%	78%	82%	85%	79%	63%	75%	72%	74%	70%	73%	75%	75%	69%	60%	76%	62%	65%	80%		62%
57.6%	66%	68%	68%	66%	69%	54%	63%	44%	51%	56%	66%	51%	42%	54%	68%	61%	36%	45%	54%	60%	68%
63.2%	65%	67%	71%	67%	69%	52%	55%	62%	56%	62%	61%	61%	60%	55%	73%	66%	65%	62%	67%	65%	67%
43.7%	46%	34%	47%	40%	58%	26%	40%	50%	46%	49%	41%	31%	50%	40%	49%	52%	41%	47%	34%	52%	44%
75.4%	79%	76%	79%	79%	71%	74%	79%	71%	75%	79%	72%	71%	79%	72%	72%	81%	71%	73%	79%	71%	80%
82.6%	74%	89%	92%	76%	82%	86%	86%	81%	84%	92%	92%	84%	84%	92%	74%	73%	69%	91%	83%	94%	57%
69.2%	61%	67%	68%	67%	68%	76%	62%	61%	68%	67%	87%	71%	68%	72%	62%	67%	68%	66%	86%	77%	65%
81.1%	79%	91%	82%	86%	76%	86%	89%	86%	88%	82%	77%	77%	72%	69%	77%	73%	89%	84%	88%	77%	75%
75.7%	79%	77%	81%	76%	74%	81%	74%	72%	80%	82%	73%	79%	79%	75%	79%	76%	71%	67%	72%	71%	71%
75.5%	77%	72%	78%	74%	77%	75%	78%	75%	78%	77%	78%	69%	77%	74%	72%	75%	70%	86%	76%	74%	74%
75.2%	69%	87%	74%	67%	68%	82%	83%	80%	80%	80%	87%	83%	74%	82%	68%	67%	66%	72%	83%	68%	60%
75.4%	81%	78%	76%	87%	87%	54%	69%	77%	76%	75%	61%	75%	82%	67%	71%	79%	87%	82%	81%		63%
69.3%	70%	70%	72%	72%	61%	72%	70%	70%	67%	74%	72%	76%	71%	68%	71%	67%	66%	56%	70%	67%	74%
76.9%	88%	72%	72%	81%	75%	71%	88%	84%	77%	75%	75%	75%	75%	75%	75%	77%	79%	76%	75%	75%	75%
67.6%	72%	66%	79%	74%	66%	73%	69%	55%	57%	62%	64%	58%	62%	58%	71%	70%	72%	63%	60%	90%	78%
69.8%	69%	73%	71%	71%	71%	83%	62%	57%	69%	73%	77%	78%	71%	74%	62%	56%	70%	79%	77%	55%	68%
94.6%	92%	96%	86%	92%	97%	92%	92%	97%	97%	92%	86%	97%	97%	92%	97%	99%	97%	99%	97%	95%	97%
71.3%	76%	73%	82%	76%	66%	61%	76%	71%	71%	76%	82%	71%	71%	76%	66%	70%	71%	70%	71%	50%	71%
77.1%	84%	69%	82%	84%	82%	72%	70%	84%	79%	79%	72%	71%	79%	72%	86%	82%	80%	77%	68%	71%
51.7%	56%	67%	72%	72%	37%	53%	50%	56%	42%	42%	42%	72%	42%	42%	50%	52%	50%	48%	42%	50%	49%
64.8%	69%	68%	67%	67%	49%	70%	69%	69%	62%	67%	67%	65%	67%	59%	59%	62%	65%	57%	70%	76%	57%
40.8%	38%	38%	42%	42%	38%	42%	33%	29%	38%	42%	56%	33%	42%	47%	41%	32%	48%	51%	47%	33%	44%
89.6%	93%	97%	93%	93%	86%	93%	86%	92%	92%	89%	88%	93%	93%	93%	92%	100%	66%	81%	100%	86%	75%
63.3%	58%	64%	72%	70%	60%	68%	68%	57%	60%	64%	76%	70%	60%	72%	57%	57%	49%	62%	66%	42%	77%
84.9%	81%	84%	75%	91%	91%	97%	81%	86%	86%	81%	75%	86%	86%	81%	91%	83%	86%	87%	86%	86%	83%
54.9%	63%	61%	66%	61%	35%	66%	53%	54%	47%	50%	61%	67%	55%	68%	44%	50%	55%	46%	68%	46%	36%
77.7%	89%	77%	75%	79%	65%	67%	79%	71%	75%	75%	76%	75%	81%	86%	84%	80%	79%	82%	79%		79%
78.5%	79%	83%	84%	84%	71%	72%	82%	55%	71%	66%	84%	90%	75%	86%	82%	80%	81%	88%	84%	71%	81%

Model Similarity Dendrogram

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