	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	3rd 72.5%	10th 69.7%	1st 72.7%	4th 72.1%	20th 65.4%	21st 65.3%	11th 69.5%	9th 70.0%	12th 69.5%	8th 70.1%	14th 68.9%	19th 65.4%	6th 70.9%	18th 66.3%	2nd 72.6%	7th 70.9%	13th 69.4%	17th 66.6%	16th 67.8%	5th 71.3%	15th 68.6%
80.5%		87%	95%	95%	60%	70%	89%	87%	95%	90%	100%	43%	90%	56%	99%	71%	70%	68%	60%	95%	89%
75.1%		84%	78%	71%	46%	66%	84%	77%	71%	75%	71%	68%	89%	74%	75%	71%	77%	82%	100%		67%
87.7%		97%	100%	95%	66%	100%	59%	83%	83%	97%	83%	88%	100%	100%	97%	97%	97%	66%	66%	83%	97%
78.0%	78%	61%	77%	90%	66%	91%	76%	91%	70%	76%	90%	91%	78%	92%	70%	63%	65%	60%	90%	91%	73%
85.7%		84%	91%	82%	84%	84%	81%	91%	84%	91%	84%	84%	84%	84%	89%	84%	89%	86%	84%	84%	90%
79.3%		89%	90%	89%	90%	58%	67%	79%	86%	74%	74%	88%	78%	71%	88%	86%	64%	88%	78%	74%	74%
54.4%		60%	60%	60%	63%	44%	47%	62%	60%	44%	39%	66%	44%	47%	60%	55%	54%	50%	47%	66%	60%
63.7%		71%	70%	81%	58%	53%	58%	62%	53%	70%	60%	43%	71%	50%	69%	72%	62%	76%	71%	66%	58%
63.5%		58%	53%	62%	71%	61%	71%	71%	76%	69%	35%	53%	69%	52%	62%	66%	63%	63%	57%	86%	72%
82.7%	91%	79%	76%	76%	91%	91%	76%	67%	91%	76%	91%	91%	91%	91%	76%	76%	76%	62%	91%	91%	86%
74.8%		100%	79%	78%	82%	75%	78%	77%	74%	55%	91%	83%	67%	74%	79%	67%	53%	47%	74%	89%
74.9%	85%	85%	77%	85%	79%	72%	66%	79%	69%	79%	77%	79%	61%	79%	72%	77%	61%	52%	79%	79%	80%
75.2%		89%	87%	87%	72%	64%	87%	87%	83%	76%	70%	53%	72%	70%	74%	84%	66%	72%	70%	79%	62%
59.8%		58%	65%	64%	46%	75%	65%	63%	63%	55%	57%	72%	55%	69%	56%	46%	55%	44%	72%	46%	70%
74.8%		65%	69%	70%	60%	78%	81%	81%	77%	69%	65%	90%	75%	60%	69%	74%	72%	90%	71%	90%	90%
76.4%		78%	86%	74%	46%	68%	77%	66%	68%	90%	90%	41%	90%	89%	95%	76%	86%	90%	66%	86%	66%
72.0%		70%	74%	74%	52%	73%	72%	76%	75%	75%	82%	65%	77%	75%	81%	75%	75%	71%	85%	61%	52%
41.9%		37%	50%	43%	46%	20%	36%	44%	42%	38%	46%	13%	38%	41%	50%	44%	60%	57%	43%	43%	46%
49.8%	51%	40%	43%	40%	56%	42%	40%	42%	67%	58%	27%	29%	58%	26%	67%	69%	76%	48%	40%	76%	51%
73.7%	80%	58%	80%	69%	68%	75%	82%	82%	71%	80%	56%	75%	80%	75%	65%	78%	85%	85%	72%	75%	56%
67.2%		61%	71%	67%	69%	76%	59%	69%	59%	71%	68%	74%	69%	61%	78%	70%	72%	63%	62%	47%	78%
72.3%		70%	69%	65%	65%	66%	70%	74%	70%	70%	70%	70%	65%	70%	74%	73%	88%	88%	70%	73%	86%
50.3%	55%	44%	50%	50%	28%	78%	55%	52%	61%	55%	66%	22%	69%	84%	44%	39%	34%	30%	61%	30%	50%
63.2%		45%	62%	62%	70%	60%	57%	57%	57%	70%	70%	70%	70%	70%	58%	66%	67%	70%	57%	56%	70%
55.2%		61%	56%	63%	46%	43%	56%	64%	46%	55%	58%	56%	53%	46%	67%	62%	60%	56%	46%	63%	47%
69.9%		88%	67%	67%	65%	61%	82%	57%	80%	65%	68%	77%	65%	67%	67%	66%	66%	62%	93%	62%	73%
75.9%		78%	85%	85%	86%	68%	73%	69%	79%	89%	67%	41%	89%	41%	90%	78%	92%	76%	61%	86%	85%
51.8%		53%	47%	47%	65%	37%	56%	53%	65%	49%	56%	41%	48%	49%	54%	49%	55%	54%	52%	52%	54%
46.3%	45%	64%	64%	58%	50%	50%	50%	44%	44%	30%	22%	22%	22%	38%	45%	57%	50%	50%	50%	50%	67%
57.9%		62%	70%	70%	70%	33%	68%	60%	62%	55%	55%	50%	60%	50%	60%	58%	63%	51%	50%	60%	52%
80.8%		79%	79%	79%	90%	75%	100%	79%	87%	79%	71%	80%	90%	71%	88%	88%	75%	66%	77%	75%	88%
62.5%		51%	51%	61%	66%	66%	66%	70%	66%	66%	66%	66%	66%	66%	56%	56%	56%	66%	66%	66%	56%
49.3%		49%	44%	48%	30%	59%	48%	48%	30%	49%	59%	59%	59%	59%	49%	49%	49%	59%	30%	59%	49%
80.7%	83%	79%	88%	88%	66%	83%	75%	83%	83%	88%	74%	75%	83%	71%	88%	83%	85%	79%	75%	88%	77%
70.0%	72%	68%	76%	76%	44%	71%	67%	70%	75%	67%	67%	91%	67%	58%	100%	90%	75%	70%	44%	70%	52%
77.0%		79%	84%	84%	62%	75%	79%	76%	76%	71%	89%	71%	77%	75%	77%	77%	76%	79%	79%	84%	71%
62.5%		63%	66%	66%	60%	60%	60%	60%	59%	60%	66%	60%	60%	66%	61%	61%	64%	66%	66%		63%
87.8%		100%	100%	100%	84%	84%	90%	91%	91%	90%	96%	81%	84%	84%	88%	90%	77%	74%	84%	91%	76%
69.9%		61%	68%	68%	75%	54%	76%	76%	61%	76%	68%	54%	76%	68%	76%	75%	77%	75%	70%	68%	76%
91.5%		97%	100%	95%	91%	66%	100%	87%	83%	97%	95%	88%	100%	100%	97%	97%	90%	83%	100%	66%	97%
67.4%		67%	76%	72%	85%	40%	76%	76%	60%	72%	83%	67%	67%	55%	62%	72%	69%	63%	55%	77%	54%
83.0%	85%	67%	85%	81%	92%	84%	83%	85%	91%	92%	71%	100%	91%	58%	85%	86%	85%	69%	85%	85%
60.1%		63%	69%	63%	52%	61%	52%	42%	44%	61%	69%	84%	52%	69%	63%	74%	55%	56%	65%	56%	52%

Model Similarity Dendrogram

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