DTeval

Loading analysis results...

Please wait while we prepare the detailed comparison.

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd3 Dtef Global Dialogues Gd3 Religion%3Ai Do Not Identify With Any Religious Group Or Faith - Run 243b965...

Global Dialogues GD3 - I do not identify with any religious group or faith

DTEF: Predict response distributions for I do not identify with any religious group or faith. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Safety

Social interaction

Knowledge, learning and memory

Best Models (Coverage)

1.Claude 3.7 Sonnet
83.7%
2.Claude Sonnet 4.5
83.4%
3.GPT 5.1
82.9%
4.Claude Haiku 4.5
82.6%
5.Llama 4 Maverick
82.3%

🔀 Least Similar Models

Claude Sonnet 4vsGPT OSS 20b

71.1% similarity

👯 Most Similar Models

Claude Haiku 4.5vsClaude Sonnet 4.5

89.6% similarity

View Blueprint

Select Prompt:

Macro Coverage Overview

Average key point coverage extent for each model across all prompts.

Pro Tip

Click on any result cell to open a detailed view.

Advanced view

Highlight best performers

Sort prompts by

Sort models by

Color Scale - Simplified View (Avg. Coverage)

Perfect

Excellent

Good

Fair

Poor

Bad

Not Met

	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	1st 83.7%	4th 82.6%	16th 75.8%	2nd 83.4%	11th 80.9%	21st 70.6%	5th 82.3%	9th 81.1%	12th 79.5%	7th 81.5%	13th 78.7%	19th 72.0%	6th 81.6%	17th 75.4%	10th 81.0%	3rd 82.9%	14th 78.4%	20th 71.5%	18th 75.0%	15th 76.2%	8th 81.2%
84.9%	89%	88%	92%	92%	87%	58%	86%	94%	85%	89%	87%	88%	91%	78%	96%	82%	79%	74%	79%	78%	90%
77.3%	72%	91%	69%	67%	87%	74%	77%	73%	82%	81%	67%	71%	77%	80%	89%	91%	73%	66%	78%	79%	79%
59.3%	66%	61%	0%	61%	63%	50%	62%	69%	63%	74%	58%	71%	69%	69%	59%	60%	63%	61%	53%	59%	54%
69.0%	67%	76%	68%	56%	63%	74%	87%	66%	67%	53%	74%	43%	74%	79%	71%	70%	70%	71%	76%	61%	82%
88.7%	89%	93%	93%	89%	87%	87%	92%	94%	93%	94%	85%	86%	85%	86%	91%	86%	86%	69%	90%	93%	95%
86.4%	88%	91%	87%	90%	88%	75%	89%	89%	89%	89%	83%	81%	89%	86%	77%	88%	89%	91%	83%	83%	89%
86.6%	93%	80%	85%	90%	80%	74%	90%	89%	93%	96%	87%	95%	91%	70%	93%	97%	92%	68%	78%	83%	94%
78.8%	86%	79%	86%	88%	75%	50%	86%	75%	83%	88%	68%	85%	89%	68%	90%	90%	82%	75%	65%	68%	78%
82.4%	79%	79%	79%	79%	89%	86%	83%	79%	79%	87%	82%	80%	85%	82%	80%	81%	83%	83%	80%	92%	83%
67.9%	70%	79%	61%	70%	73%	69%	82%	65%	62%	55%	71%	35%	68%	69%	69%	71%	76%	79%	71%	60%	70%
78.0%	84%	83%	84%	96%	71%	87%	66%	86%	77%	83%	82%	85%	81%	67%	86%	85%	63%	51%	84%	55%	82%
70.9%	76%	84%	70%	70%	83%	62%	77%	66%	60%	55%	72%	32%	66%	68%	81%	77%	89%	77%	72%	72%	80%
80.7%	87%	87%	91%	84%	87%	83%	76%	84%	75%	86%	83%	47%	77%	85%	84%	84%	82%	67%	84%	78%	84%
84.7%	90%	91%	92%	77%	94%	95%	92%	89%	91%	74%	90%	71%	87%	92%	84%	86%	85%	63%	86%	72%	78%
81.8%	86%	89%	88%	87%	78%	71%	88%	87%	86%	86%	78%	70%	86%	79%	83%	85%	81%	73%	76%	84%	76%
81.9%	88%	85%	90%	92%	81%	63%	88%	91%	82%	90%	84%	87%	89%	66%	88%	89%	80%	71%	66%	65%	85%
70.9%	73%	85%	76%	83%	80%	70%	73%	53%	69%	68%	61%	73%	55%	59%	87%	81%	63%	63%	71%	64%	81%
73.4%	75%	75%	75%	85%	69%	47%	84%	79%	69%	75%	73%	77%	77%	65%	82%	77%	72%	70%	64%	75%	77%
67.0%	71%	50%	75%	75%	50%	48%	75%	69%	65%	84%	65%	71%	67%	63%	82%	75%	56%	51%	55%	78%	81%
86.4%	91%	68%	86%	85%	90%	88%	89%	94%	91%	90%	88%	87%	85%	82%	82%	91%	88%	82%	82%	92%	83%
81.9%	91%	86%	90%	89%	82%	70%	87%	90%	87%	89%	78%	69%	86%	77%	82%	88%	77%	73%	73%	79%	76%
87.4%	88%	90%	94%	88%	90%	70%	91%	89%	87%	92%	88%	82%	94%	84%	94%	91%	83%	82%	85%	88%	86%
81.5%	96%	83%	83%	84%	84%	74%	96%	87%	80%	86%	79%	54%	80%	78%	90%	91%	75%	66%	83%	82%	81%
85.9%	95%	91%	91%	95%	89%	90%	86%	91%	86%	89%	87%	54%	81%	88%	89%	87%	77%	74%	86%	86%	92%
83.3%	87%	88%	92%	91%	92%	88%	85%	90%	91%	75%	89%	76%	82%	89%	83%	77%	85%	66%	82%	67%	74%
79.7%	87%	85%	87%	87%	87%	74%	78%	65%	79%	89%	84%	71%	81%	83%	87%	86%	80%	62%	79%	66%	77%
78.8%	84%	80%	88%	86%	79%	53%	82%	82%	80%	84%	70%	79%	80%	63%	89%	87%	76%	77%	74%	75%	86%
80.6%	92%	94%	85%	93%	91%	43%	75%	87%	79%	83%	80%	82%	89%	59%	90%	90%	80%	80%	60%	76%	85%
66.9%	71%	75%	73%	76%	69%	57%	78%	74%	53%	59%	72%	26%	72%	59%	77%	75%	66%	71%	55%		79%
74.0%	72%	82%	72%	80%	70%	62%	72%	71%	73%	79%	80%	71%	72%	71%	80%	82%	77%	70%	67%	72%	79%
87.0%	91%	92%	95%	94%	90%	78%	89%	90%	89%	90%	84%	66%	93%	88%	95%	91%	84%	72%	82%		87%
79.8%	82%	85%	0%	84%	82%	96%	83%	76%	82%	71%	88%	74%	76%	76%	87%	87%	82%	82%	93%	95%	95%
57.0%	60%	58%	0%	59%	61%	48%	60%	67%	61%	72%	55%	69%	67%	67%	62%	58%	61%	61%	51%	49%	52%
84.0%	95%	78%	84%	89%	93%	66%	86%	89%	82%	89%	74%	86%	91%	60%	93%	91%	87%	82%	67%	95%	86%
75.4%	78%	84%	73%	72%	64%	66%	65%	69%	75%	73%	76%	67%	87%	92%	63%	66%	84%	84%	87%	80%	78%
76.6%	77%	85%	79%	70%	76%	80%	85%	86%	72%	74%	78%	78%	82%	72%	66%	79%	76%	68%	72%	73%	81%
83.1%	96%	85%	93%	93%	85%	76%	86%	85%	85%	89%	83%	68%	89%	76%	82%	86%	79%	66%	77%	82%	84%
80.8%	96%	86%	91%	96%	95%	76%	83%	78%	84%	93%	71%	69%	87%	66%	87%	82%	69%	62%	72%	67%	87%
78.0%	91%	81%	82%	95%	81%	54%	79%	83%	83%	82%	76%	80%	84%	69%	88%	86%	73%	72%	64%	66%	69%
85.0%	99%	99%	0%	98%	96%	89%	97%	90%	96%	85%	98%	88%	90%	90%	0%	99%	96%	96%	93%	96%	89%
83.0%	92%	87%	94%	88%	86%	63%	86%	87%	92%	91%	85%	83%	86%	69%	86%	86%	89%	50%	73%	82%	88%
80.6%	77%	84%	80%	80%	76%	69%	90%	82%	78%	86%	82%	87%	89%	87%	76%	74%	82%	73%	77%	82%	82%
83.0%	82%	79%	87%	82%	87%	82%	80%	87%	85%	87%	88%	83%	84%	87%	85%	81%	82%	81%	80%	76%	79%

Model Similarity Dendrogram

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