	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	3rd 73.4%	10th 67.7%	9th 67.9%	2nd 73.7%	5th 70.6%	21st 56.2%	13th 64.9%	7th 69.0%	11th 67.1%	1st 74.2%	12th 65.4%	13th 64.9%	8th 68.6%	16th 63.3%	4th 71.3%	6th 70.1%	19th 59.0%	15th 64.3%	18th 61.7%	17th 61.8%	20th 58.6%
76.0%	88%	80%	77%	86%	81%	50%	66%	75%	74%	92%	70%	75%	74%	70%	94%	83%	64%	83%	64%	86%	65%
77.9%	80%	87%	87%	87%	80%	83%	76%	87%	72%	76%	81%	77%	81%	77%	73%	65%	82%	53%	80%	73%	78%
76.1%	71%	66%	84%	84%	89%	80%	74%	85%	77%	80%	80%	77%	75%	74%	75%	83%	72%	68%	66%	68%	71%
34.7%	36%	34%	33%	33%	42%	38%	39%	43%	42%	38%	37%	31%	38%	49%	25%	30%	23%	29%	45%	28%	15%
76.4%	76%	84%	77%	78%	74%	75%	69%	74%	80%	81%	80%	89%	79%	84%	67%	67%	73%	75%	84%	71%	67%
58.4%	66%	59%	66%	66%	65%	41%	59%	62%	61%	64%	51%	61%	59%	48%	64%	66%	47%	57%	48%		58%
62.4%	71%	56%	67%	75%	64%	59%	59%	63%	61%	80%	62%	68%	62%	46%	76%	64%	47%	62%	55%	57%	57%
56.0%	71%	53%	50%	70%	60%	27%	49%	54%	58%	79%	47%	66%	55%	47%	73%	77%	40%	57%	34%	62%	46%
65.8%	79%	68%	68%	75%	75%	42%	52%	72%	60%	75%	68%	71%	69%	69%	76%	76%	59%	52%	52%	68%	55%
32.8%	32%	38%	29%	45%	41%	32%	31%	41%	38%	46%	32%	27%	33%	44%	28%	27%	23%	24%	41%	22%	14%
80.4%	86%	87%	71%	72%	88%	86%	77%	83%	87%	85%	79%	82%	84%	72%	71%	76%	87%	87%	88%	81%	60%
28.1%	33%	37%	30%	30%	34%	26%	20%	40%	37%	38%	39%	24%	31%	33%	23%	25%	16%	18%	37%	10%	10%
80.5%	93%	80%	79%	88%	84%	61%	84%	85%	80%	87%	68%	82%	84%	77%	91%	88%	74%	82%	66%		76%
81.1%	88%	81%	75%	94%	75%	78%	77%	86%	80%	91%	80%	93%	80%	70%	89%	87%	79%	87%	73%	74%	66%
87.0%	95%	89%	86%	84%	92%	84%	89%	75%	78%	91%	88%	76%	90%	87%	94%	93%	90%	86%	87%	90%	83%
70.1%	82%	76%	73%	87%	90%	41%	64%	74%	70%	84%	71%	62%	72%	58%	80%	82%	54%	65%	52%	75%	60%
57.2%	73%	61%	61%	65%	77%	47%	60%	43%	53%	60%	46%	45%	58%	45%	71%	63%	49%	49%	60%	53%	63%
54.1%	63%	58%	60%	65%	56%	28%	46%	55%	52%	65%	52%	55%	54%	50%	68%	64%	46%	50%	47%	54%	49%
55.5%	63%	64%	53%	67%	43%	48%	57%	64%	55%	64%	58%	46%	57%	61%	45%	51%	56%	54%	74%	51%	34%
72.6%	75%	58%	67%	82%	74%	63%	70%	73%	75%	87%	71%	79%	65%	57%	84%	78%	70%	90%	58%	73%	75%
69.5%	88%	78%	62%	82%	67%	45%	75%	71%	71%	89%	67%	69%	71%	62%	91%	91%	56%	72%	48%	48%	57%
78.0%	93%	71%	80%	92%	83%	56%	79%	87%	79%	90%	76%	75%	83%	76%	92%	93%	65%	76%	62%	63%	68%
61.5%	68%	62%	59%	75%	68%	58%	68%	58%	56%	68%	60%	33%	62%	71%	76%	57%	33%	75%	76%	77%	31%
75.3%	83%	75%	88%	86%	74%	58%	78%	82%	74%	84%	63%	74%	82%	77%	78%	81%	68%	72%	61%	73%	71%
86.7%	93%	81%	86%	87%	83%	84%	89%	91%	89%	85%	91%	90%	96%	80%	87%	86%	91%	82%	87%	82%	80%
76.1%	85%	76%	80%	81%	82%	61%	71%	73%	77%	78%	79%	77%	82%	73%	79%	78%	69%	77%	68%	78%	74%
57.3%	76%	60%	67%	73%	59%	32%	52%	63%	57%	74%	44%	60%	61%	44%	63%	69%	41%	53%	42%	65%	49%
67.1%	69%	74%	72%	77%	71%	41%	66%	83%	73%	89%	58%	69%	71%	51%	81%	81%	49%	63%	57%	49%	66%
30.3%	33%	37%	32%	34%	34%	23%	29%	30%	28%	30%	36%	13%	36%	43%	35%	31%	33%	39%	30%	21%	10%
41.2%	41%	37%	43%	42%	50%	34%	27%	35%	34%	47%	48%	42%	40%	42%	43%	39%	39%	63%	42%	44%	34%
77.0%	89%	83%	80%	84%	76%	77%	73%	72%	74%	60%	81%	75%	77%	79%	73%	67%	80%	76%	76%	84%	82%
83.7%	85%	94%	76%	76%	71%	80%	86%	75%	83%	80%	80%	83%	85%	86%	80%	80%	88%	92%	94%	94%	89%
63.6%	64%	54%	70%	71%	76%	67%	62%	72%	64%	67%	67%	64%	62%	62%	66%	67%	60%	56%	54%	51%	59%
71.8%	82%	64%	70%	87%	90%	58%	57%	75%	70%	85%	65%	67%	68%	51%	80%	76%	73%	67%	60%	81%	81%
34.1%	39%	39%	32%	39%	29%	26%	29%	34%	34%	50%	33%	33%	44%	45%	23%	34%	27%	24%	48%	34%	20%
69.7%	79%	74%	71%	85%	82%	54%	76%	76%	67%	85%	72%	63%	77%	59%	84%	75%	54%	57%	49%	57%	68%
86.2%	92%	88%	94%	86%	90%	81%	92%	82%	90%	76%	85%	80%	90%	85%	92%	85%	86%	81%	79%	85%	91%
81.9%	83%	90%	81%	89%	79%	87%	81%	75%	86%	83%	86%	85%	86%	73%	80%	81%	79%	80%	92%	68%	76%
66.5%	78%	67%	64%	74%	69%	47%	84%	80%	74%	89%	65%	68%	85%	65%	86%	85%	49%	54%	52%	10%	51%
92.6%	92%	83%	99%	99%	93%	98%	92%	97%	95%	97%	97%	94%	92%	92%	92%	97%	90%	86%	83%	86%	91%
65.1%	69%	58%	72%	71%	80%	45%	80%	75%	78%	81%	63%	56%	70%	54%	70%	73%	40%	55%	46%		65%
69.1%	73%	73%	67%	66%	67%	57%	68%	77%	72%	74%	70%	73%	69%	73%	73%	73%	58%	70%	72%	70%	57%
67.3%	83%	75%	83%	80%	80%	60%	57%	69%	69%	68%	67%	60%	61%	61%	74%	70%	60%	68%	66%	55%	48%

Model Similarity Dendrogram

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