	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
Score	- -	6th 77.6%	2nd 78.9%	1st 80.0%	9th 76.7%	13th 75.7%	4th 77.9%	13th 75.7%	12th 76.2%	5th 77.7%	3rd 78.3%	17th 70.8%	15th 75.5%	10th 76.6%	11th 76.6%	8th 77.0%	16th 72.4%	20th 67.7%	7th 77.6%	18th 70.4%	19th 67.7%
79.6%		73%	81%	82%	71%	75%	89%	79%	87%	84%	82%	82%	80%	89%	79%	75%	77%	66%	82%	84%	75%
72.5%		74%	77%	79%	73%	82%	71%	70%	53%	76%	77%	74%	68%	77%	77%	76%	74%	62%	78%	71%	62%
72.8%		68%	77%	71%	71%	73%	68%	69%	66%	77%	77%	80%	71%	68%	68%	69%	74%	75%	62%	99%	74%
77.5%		72%	76%	78%	86%	71%	81%	81%	84%	71%	75%	79%	75%	81%	81%	86%	72%	73%	76%	72%	80%
86.9%		83%	95%	95%	87%	93%	99%	86%	92%	89%	77%	76%	89%	89%	93%	91%	89%	66%	94%		69%
86.3%		88%	83%	83%	87%	88%	86%	99%	90%	87%	90%	90%	88%	87%	83%	78%	86%	89%	83%	85%	75%
77.3%		79%	81%	85%	84%	74%	81%	88%	88%	71%	81%	56%	67%	74%	76%	80%	81%	71%	80%	78%	70%
76.7%		84%	78%	76%	78%	60%	85%	76%	79%	84%	81%	76%	81%	80%	70%	76%	73%	65%	76%	71%	85%
67.8%		67%	69%	66%	78%	74%	74%	76%	78%	70%	70%	76%	68%	67%	52%	56%	55%	70%	70%	66%	55%
77.5%		86%	75%	81%	86%	86%	75%	69%	76%		79%		76%	75%	79%	82%	69%	67%	81%	69%	84%
58.6%		67%	67%	72%	48%	70%	53%	74%	62%	52%	68%	50%	58%	52%	76%	55%	38%	28%	80%	61%	41%
86.1%			91%	80%	80%	82%	89%	86%	88%	88%	87%	85%		95%	88%	84%	80%	88%	91%	87%	80%
67.3%		70%	75%	80%	75%	68%	66%	52%	62%	79%	79%	45%	70%	68%	68%	69%	64%	61%	81%	70%	44%
81.1%		89%	84%	81%	76%	95%	81%	84%	87%	89%	79%	84%	85%	84%		71%	76%	76%	77%	74%	68%
78.5%		78%	78%	80%	81%	82%	74%	73%	74%	80%	83%	70%	75%	78%	74%	87%	78%	78%	83%	83%	82%
75.8%		74%	79%	74%	76%	72%	79%	79%	73%	79%	75%	77%	79%	81%	78%	78%	73%	70%	77%	68%	74%
81.3%		87%	86%	91%	91%	83%	80%	63%	84%	82%	87%	67%	75%	83%	91%	87%	83%	67%	84%	78%	77%
74.7%		72%	79%	86%	94%	51%	70%	85%	72%	79%	70%	70%	83%	64%	77%	82%	82%	40%	72%	80%	85%
45.4%		29%	51%	49%	55%	33%	46%	48%	42%	49%	46%		48%	48%	60%	53%	40%	48%	33%	47%	38%
79.2%		77%	85%	85%	81%	81%		70%	81%	75%	87%	62%	74%	85%	83%	83%	77%	88%	91%	63%	77%
74.9%		78%	83%	77%	76%	88%	81%	63%	76%	75%	78%	73%	81%	88%	65%	63%	67%	63%	92%	77%	53%
69.4%		75%	75%	76%	62%	81%	76%	63%	66%	68%	76%	59%	74%	74%	66%	76%	53%	67%	78%	67%	56%
70.6%		69%	60%	62%	86%	81%	80%	88%	77%	65%	80%	55%	69%	85%	66%	69%	65%	69%	66%	58%	63%
60.7%		68%	74%	72%	63%	66%	45%	48%	57%	66%	63%	39%	60%	53%	76%	72%	49%	62%	76%	71%	35%
77.5%		83%	83%	79%	81%	88%	83%	78%	76%	75%	83%	80%	82%	75%	76%	72%	69%	71%	82%	72%	61%
68.4%		89%	79%	71%	72%	82%	72%	58%	68%	69%	78%	74%	62%	81%	58%	59%	53%	62%	75%	56%	50%
78.3%		80%	86%	83%	79%	52%	84%	88%	80%	87%	70%	80%	77%	73%	83%	87%	88%	69%	74%	71%	75%
73.1%		78%	76%	74%	63%	69%	79%	78%	70%	79%	78%	72%	75%	74%	72%	75%	77%	65%	74%	72%	62%
69.4%		92%	84%	80%	75%	64%	80%	68%	67%	61%	74%	55%	60%	60%	74%	67%	65%	58%	68%	67%
82.7%		86%	86%	99%	95%	65%	79%	78%	82%	84%	84%	69%	79%	76%	88%	85%	88%	87%	81%	79%	83%
69.9%		74%	76%	77%	72%	81%	69%	68%	67%	81%	83%	65%	72%	77%	82%	80%	71%	75%	76%	10%	41%
85.9%		91%	82%	88%	88%	85%	91%	90%	93%	82%	82%	79%	88%	91%	88%	90%	85%	84%	97%	59%	85%
78.3%		73%	82%	76%	76%	79%	73%	74%	71%	82%	82%	85%	76%	73%	76%	74%	79%	80%	67%	94%	94%
81.5%		80%	78%	86%	75%	73%	85%	89%	90%	87%	84%	86%		71%	85%	89%	85%	78%	72%	74%
79.4%		82%	87%	90%	43%	87%	78%	84%	85%	85%	83%	73%	88%	78%	82%	82%	82%	74%	73%	80%	72%
77.5%		84%	88%	93%	63%	70%	87%	85%	76%	82%	86%	76%	83%	76%	77%	82%	75%	68%	77%	65%	57%
69.2%		71%	74%	75%	65%	71%	74%	67%	66%	74%	71%	66%	73%	71%	71%	72%	66%	61%	68%	64%	64%
75.4%		82%	97%	99%	91%	88%	96%	78%	88%	88%	88%	59%	81%	74%	71%	77%	55%	38%	83%	37%	37%
77.3%		86%	79%	83%	77%	85%	78%	75%	79%	80%	80%	74%	80%	82%	76%	82%	80%	59%	70%	72%	68%
85.9%		91%	82%	88%	88%	85%	91%	90%	93%	82%	82%	79%	88%	91%	88%	90%	85%	84%	97%	59%	85%
71.5%		73%	68%	72%	80%	63%	73%	79%	79%	83%	72%	50%	74%	70%	78%	80%	67%	25%	79%	82%	83%
76.9%		82%	70%	75%	76%	66%	76%	75%	70%	82%	83%	76%	75%	87%	81%	78%	78%	77%	76%	76%	80%
85.5%		77%	77%	91%	94%	92%	93%	83%	84%	84%	76%	78%	87%	90%	85%	93%	89%	85%	84%	89%	78%

Model Similarity Dendrogram

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