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: Gd6 Dtef Global Dialogues Gd6 Religion%3Ai Do Not Identify With Any Religious Group Or Faith - Run 16a3d67...

Global Dialogues GD6 - 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 GD6 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Data Privacy & Bodily Autonomy

AI Safety & Robustness

Economic Disruption & Reskilling Advice

General Knowledge

Reasoning

Trust

Best Models (Coverage)

1.Claude Haiku 4.5
79.3%
2.Gemini 2.5 Flash
79.2%
3.GPT 4.1 Mini
76.4%
4.GPT 4o Mini
75.1%
5.GPT 4.1 Nano
71.7%

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 Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 79.3%	2nd 79.2%	6th 69.8%	3rd 76.4%	5th 71.7%	4th 75.1%
42.5%	31%	60%	34%	42%	44%	44%
77.2%	80%	92%	68%	73%	88%	62%
80.0%	79%	80%	75%	86%	90%	70%
80.8%	92%	90%	59%	85%	88%	71%
75.0%	79%	92%	83%	78%	40%	78%
79.5%	86%	74%	89%	83%	82%	63%
86.0%	83%	85%	82%	94%	84%	88%
68.0%	82%	79%	54%	62%	63%	68%
67.2%	58%	63%	74%	57%	94%	57%
73.3%	84%	79%	73%	66%	51%	87%
80.0%	77%	83%	83%	81%	76%	80%
81.0%	90%	80%	79%	76%	88%	73%
70.7%	89%	74%	63%	71%	53%	74%
87.2%	89%	85%	92%	89%	82%	86%
58.5%	61%	62%	57%	45%	79%	47%
86.7%	95%	94%	66%	91%	88%	86%
77.2%	86%	88%	80%	71%	50%	88%
62.7%	70%	60%	65%	68%	53%	60%
75.7%	86%	89%	61%	85%	71%	62%
51.2%	64%	54%	41%	63%	37%	48%
78.0%	79%	80%	77%	80%	67%	85%
74.0%	82%	80%	52%	72%	86%	72%
84.8%	92%	86%	87%	82%	76%	86%
69.0%	69%	57%	69%	76%	65%	78%
48.0%	43%	48%	46%	47%	45%	59%
83.3%	95%	76%	69%	78%	90%	92%
86.8%	90%	88%	93%	76%	83%	91%
68.5%	72%	75%	59%	73%	66%	66%
80.3%	85%	82%	80%	81%	72%	82%
70.0%	91%	77%	36%	76%	81%	59%
66.2%	73%	65%	66%	67%	53%	73%
75.5%	77%	79%	74%	79%	77%	67%
77.2%	85%	91%	77%	76%	55%	79%
76.2%	89%	74%	75%	76%	65%	78%
73.8%	76%	80%	76%	72%	56%	83%
72.0%	72%	67%	78%	74%	64%	77%
71.8%	86%	63%	71%	64%	70%	77%
74.5%	70%	64%	80%	75%	72%	86%
84.0%	87%	94%	78%	83%	79%	83%
68.8%	79%	71%	48%	75%	76%	64%
80.2%	87%	77%	60%	88%	89%	80%
74.8%	88%	60%	68%	71%	71%	91%
78.0%	84%	87%	76%	84%	57%	80%
76.2%	81%	82%	60%	82%	82%	70%
88.8%	94%	92%	84%	85%	83%	95%
56.3%	64%	57%	43%	50%	56%	68%
80.0%	75%	71%	90%	86%	68%	90%
75.3%	70%	71%	78%	75%	75%	83%
81.8%	86%	81%	75%	85%	83%	81%
82.7%	88%	84%	69%	94%	80%	81%
63.7%	75%	72%	47%	66%	61%	61%
72.5%	80%	83%	55%	78%	78%	61%
80.8%	85%	85%	77%	87%	69%	82%
75.8%	86%	92%	68%	72%	68%	69%
85.7%	86%	89%	85%	80%	89%	85%
66.7%	78%	93%	42%	67%	54%	66%
61.3%	72%	58%	55%	74%	55%	54%
70.3%	84%	87%	48%	70%	78%	55%
89.2%	90%	93%	96%	88%	79%	89%
84.7%	91%	80%	68%	89%	90%	90%
69.5%	79%	73%	53%	69%	81%	62%
79.2%	71%	86%	85%	84%	67%	82%
82.5%	68%	86%	86%	87%	85%	83%
78.8%	80%	81%	82%	80%	69%	81%
83.0%	68%	88%	89%	85%	86%	82%
80.0%	75%	87%	87%	81%	75%	75%
85.0%	88%	84%	89%	78%	85%	86%
78.2%	80%	73%	78%	86%	67%	85%
77.8%	77%	77%	85%	76%	83%	69%
78.2%	83%	72%	86%	81%	73%	74%
82.0%	91%	91%	92%	86%	53%	79%
62.7%	86%	76%	54%	63%	38%	59%
62.0%	52%	77%	48%	54%	76%	65%
82.8%	73%	76%	80%	90%	89%	89%
67.2%	78%	65%	66%	68%	57%	69%
86.7%	84%	84%	90%	90%	79%	93%
85.7%	93%	80%	68%	91%	91%	91%
71.3%	47%	83%	68%	72%	79%	79%
86.8%	93%	93%	71%	91%	84%	89%
51.2%	66%	82%	10%	58%	45%	46%
60.5%	78%	88%	50%	59%	48%	40%
79.0%	86%	84%	69%	77%	74%	84%
72.2%	79%	76%	50%	70%	88%	70%
79.2%	87%	83%	75%	86%	69%	75%
82.3%	71%	92%	83%	82%	82%	84%
81.2%	88%	81%	66%	90%	85%	77%
68.8%	81%	82%	58%	64%	55%	73%
81.0%	67%	89%	76%	86%	82%	86%
76.3%	84%	95%	69%	71%	70%	69%
89.0%	92%	86%	88%	91%	88%	89%
80.2%	73%	83%	87%	85%	60%	93%