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: Gd4 Dtef Global Dialogues Gd4 Religion%3Ai Do Not Identify With Any Religious Group Or Faith - Run 2580c74...

Global Dialogues GD4 - 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 GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

AI Safety & Robustness

Social interaction

Economic Disruption & Reskilling Advice

Trust in Institutions

Demographic Analysis

Best Models (Coverage)

1.Claude Haiku 4.5
80.0%
2.Gemini 2.5 Flash
79.2%
3.Gemma 3 12b It
79.0%
4.GPT 4.1 Mini
78.1%
5.GPT 4o Mini
76.0%

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 80.0%	2nd 79.2%	3rd 79.0%	4th 78.1%	6th 74.5%	5th 76.0%
73.6%	79%	70%		76%	77%	66%
71.8%	72%	77%		63%	70%	77%
79.0%	80%	86%		81%	72%	76%
83.8%	88%	82%		83%	85%	81%
67.0%	71%	73%		65%	64%	62%
67.4%	86%	0%		77%	91%	83%
53.2%	68%	59%		57%	31%	51%
74.2%	66%	61%		70%	85%	89%
83.0%	85%	81%		89%	81%	79%
83.0%	84%	67%		86%	89%	89%
84.0%	89%	84%		83%	83%	81%
79.0%	88%	92%		85%	52%	78%
80.8%	82%	83%		83%	83%	73%
50.6%	87%	0%		58%	54%	54%
68.8%	67%	53%		75%	72%	77%
78.2%	88%	97%		76%	58%	72%
83.4%	84%	85%		85%	76%	87%
89.0%	91%	92%		91%	82%	89%
85.2%	88%	85%	79%	88%	86%	85%
86.4%	89%	80%		87%	87%	89%
88.0%	91%	91%		90%	78%	90%
89.0%	92%	96%		89%	86%	82%
81.6%	81%	81%		74%	90%	82%
55.2%	67%	56%		52%	57%	44%
75.4%	80%	86%		64%	78%	69%
64.0%	74%	69%		67%	45%	65%
82.6%	68%	89%		88%	87%	81%
82.8%	82%	88%		80%	91%	73%
73.4%	77%	85%		69%	75%	61%
81.8%	84%	84%		84%	83%	74%
82.6%	88%	82%		88%	70%	85%
79.4%	71%	82%		81%	82%	81%
84.2%	87%	88%		83%	93%	70%
64.0%	70%	84%		50%	50%	66%
68.8%	65%	82%		58%	67%	72%
84.0%	87%	75%		85%	87%	86%
66.2%	66%	48%		59%	77%	81%
73.8%	81%	78%			68%	68%
87.0%	88%	86%		91%	84%	86%
75.4%	65%	67%		84%	86%	75%
80.8%	92%	85%		73%	63%	91%
82.6%	88%	77%		87%	88%	73%
82.8%	78%	78%		85%	94%	79%
71.6%	62%	69%		72%	87%	68%
82.8%	91%	77%		83%	82%	81%
80.6%	88%	80%		79%	76%	80%
86.0%	90%	93%		84%	86%	77%
91.8%	92%	95%		98%	94%	80%
86.2%	87%	93%		83%	92%	76%
80.8%	92%	86%		80%	66%	80%
80.2%	91%	80%		79%	71%	80%
62.2%	56%	78%		63%	58%	56%
75.8%	76%	84%		76%	72%	71%
55.2%	62%	69%		53%	39%	53%
81.8%	83%	78%		83%	83%	82%
78.0%	80%	85%		76%	87%	62%
59.0%	52%	60%		59%	69%	55%
88.0%	91%	89%		94%	84%	82%
56.8%	63%	79%		58%	26%	58%
76.6%	79%	75%		78%	72%	79%
81.4%	88%	86%		91%	74%	68%
73.6%	78%	77%		71%	78%	64%
79.4%	88%	95%		71%	74%	69%
87.8%	90%	84%		87%	91%	87%
81.2%	84%	72%		76%	91%	83%
80.3%	88%	85%			84%	64%
72.6%	83%	85%		68%	73%	54%
73.6%	79%	75%		77%	66%	71%
77.0%	76%	74%		75%	82%	78%
84.2%	74%	93%		82%	85%	87%
81.6%	85%	86%		78%	72%	87%
83.6%	87%	71%		94%	83%	83%
87.6%	91%	90%		81%	88%	88%
62.8%	64%	67%		65%	57%	61%
76.4%	80%	85%		70%	65%	82%
76.2%	73%	82%		82%	66%	78%
82.0%	80%	85%		81%	82%	82%
86.4%	92%	87%		88%	88%	77%
81.2%	82%	82%		82%	77%	83%
81.4%	85%	76%		81%	82%	83%
87.8%	90%	96%		87%	83%	83%
83.8%	90%	90%		87%	65%	87%
72.2%	72%	67%		78%	74%	70%
85.4%	86%	93%		89%	71%	88%
82.0%	79%	87%		85%	75%	84%
83.4%	86%	82%		87%	80%	82%
69.8%	69%	75%		61%	64%	80%
84.4%	88%	83%		87%	77%	87%
61.0%	70%	81%		57%	43%	54%
82.4%	87%	86%		86%	79%	74%
75.4%	76%	74%		79%	74%	74%
52.4%	31%	62%		45%	62%	62%
74.6%	83%	65%		73%	65%	87%
82.6%	87%	83%		86%	80%	77%
69.8%	71%	76%		68%	67%	67%
79.6%	72%	82%		75%	84%	85%
74.5%	85%	69%			69%	75%
82.4%	80%	73%		90%	86%	83%
73.8%	76%	93%		80%	53%	67%
80.8%	86%	89%		81%	62%	86%
67.8%	69%	75%			63%	64%
84.6%	81%	91%		86%	95%	70%
65.0%	79%	65%		69%	50%	62%
85.2%	82%	91%		86%	83%	84%
88.6%	93%	89%		89%	84%	88%
88.2%	88%	88%		89%	86%	90%
71.8%	81%	87%		70%	62%	59%
72.6%	72%	80%		73%	69%	69%
72.2%	80%	83%		77%	46%	75%
86.4%	81%	82%		93%	97%	79%
81.2%	73%	85%		74%	87%	87%
83.2%	88%	88%		88%	63%	89%
65.8%	74%	62%		71%	49%	73%
85.4%	86%	88%		88%	81%	84%
85.6%	80%	95%		89%	75%	89%
77.6%	73%	78%		84%	77%	76%