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: Gd6uk Dtef Global Dialogues Gd6uk Religion%3Ai Do Not Identify With Any Religious Group Or Faith - Run def4ad0...

Global Dialogues GD6UK - 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 GD6UK (https://github.com/collect-intel/global-dialogues)

TAGS:

PERIODIC

Dtef

Demographic

Global Dialogues Gd6uk

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.Gemini 2.5 Flash
78.9%
2.Claude Haiku 4.5
76.3%
3.GPT 4.1 Mini
73.7%
4.GPT 4o Mini
72.7%
5.GPT 4.1 Nano
69.0%

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	2nd 76.3%	1st 78.9%	6th 67.9%	3rd 73.7%	5th 69.0%	4th 72.7%
73.8%	72%	73%	80%	68%	62%	88%
78.0%	84%	71%	71%	87%	75%	80%
76.7%	75%	82%	76%	72%	77%	78%
74.3%	86%	82%	61%	80%	67%	70%
75.3%	88%	74%	67%	77%	79%	67%
88.3%	89%	86%	88%	89%	89%	89%
69.7%	46%	85%	63%	72%	76%	76%
84.8%	84%	93%	86%	81%	81%	84%
70.3%	70%	79%	51%	88%	62%	72%
82.8%	83%	79%	88%	79%	80%	88%
45.3%	48%	60%	45%	35%	48%	36%
60.3%	71%	80%	57%	53%	49%	52%
50.2%	60%	46%	40%	39%	53%	63%
71.3%	72%	89%	74%	73%	49%	71%
80.8%	69%	91%	75%	85%	78%	87%
70.5%	70%	76%	60%	74%	64%	79%
82.8%	87%	83%	83%	85%	75%	84%
88.3%	89%	94%	92%	86%	81%	88%
55.2%	43%	69%	41%	45%	79%	54%
65.0%	70%	58%	70%	71%	67%	54%
77.2%	73%	81%	81%	77%	75%	76%
81.2%	70%	80%	91%	84%	80%	82%
91.5%	99%	97%	72%	97%	92%	92%
74.8%	90%	47%	86%	83%	69%	74%
78.0%	62%	89%	84%	83%	73%	77%
67.2%	76%	75%	49%	68%	64%	71%
78.3%	79%	74%	76%	82%	73%	86%
67.5%	57%	68%	76%	54%	93%	57%
79.7%	79%	79%	76%	81%	79%	84%
70.5%	58%	72%	89%	65%	54%	85%
73.3%	81%	85%	74%	72%	47%	81%
89.5%	92%	92%	93%	90%	78%	92%
79.0%	86%	84%	67%	79%	75%	83%
89.7%	90%	89%	81%	92%	92%	94%
83.3%	73%	90%	83%	88%	81%	85%
78.3%	85%	85%	67%	85%	71%	77%
76.2%	80%	80%	69%	76%	76%	76%
67.3%	76%	84%	55%	69%	70%	50%
72.0%	72%	73%	73%	78%	63%	73%
61.3%	71%	62%	53%	51%	69%	62%
68.0%	86%	71%	63%	71%	44%	73%
75.8%	82%	83%	71%	77%	67%	75%
50.0%	69%	50%	45%	46%	58%	32%
72.7%	80%	78%	55%	77%	77%	69%
79.5%	76%	79%	87%	76%	78%	81%
72.7%	75%	68%	76%	73%	63%	81%
70.2%	77%	77%	63%	62%	83%	59%
78.8%	83%	92%	73%	76%	76%	73%
79.2%	84%	90%	69%	84%	73%	75%
77.8%	84%	84%	76%	81%	61%	81%
37.8%	32%	48%	33%	40%	32%	42%
81.2%	80%	88%	83%	73%	80%	83%
79.7%	85%	85%	83%	79%	60%	86%
86.5%	86%	94%	86%	84%	83%	86%
68.0%	78%	74%	68%	56%	50%	82%
79.2%	87%	85%	94%	84%	47%	78%
62.0%	77%	68%	54%	71%	39%	63%
85.2%	77%	89%	88%	91%	79%	87%
87.5%	89%	93%	77%	86%	89%	91%
73.8%	82%	78%	64%	75%	72%	72%
79.7%	89%	85%	76%	79%	65%	84%
50.0%	61%	76%	27%	54%	41%	41%
70.8%	77%	74%	68%	78%	54%	74%
77.8%	81%	91%	70%	75%	87%	63%
73.3%	83%	80%	67%	77%	55%	78%
59.3%	72%	94%	25%	46%	76%	43%
76.5%	72%	71%	80%	79%	71%	86%
80.0%	79%	85%	79%	82%	73%	82%
56.3%	65%	86%	31%	60%	43%	53%
64.0%	79%	73%	50%	62%	70%	50%
75.8%	76%	87%	80%	76%	70%	66%
81.2%	75%	78%	81%	87%	77%	89%
76.7%	83%	91%	52%	80%	83%	71%
67.3%	78%	83%	51%	71%	66%	55%
62.5%	72%	75%	63%	69%	30%	66%
79.0%	90%	89%	78%	77%	69%	71%
59.2%	70%	58%	53%	71%	52%	51%
70.3%	56%	85%	73%	68%	70%	70%
84.3%	92%	81%	65%	90%	95%	83%
71.2%	80%	78%	64%	66%	64%	75%
70.3%	75%	77%	71%	71%	63%	65%
61.5%	73%	62%	41%	68%	73%	52%
64.3%	80%	82%	10%	63%	75%	76%
84.0%	84%	81%	86%	79%	93%	81%
57.8%	68%	59%	55%	56%	51%	58%
77.8%	85%	91%	54%	83%	82%	72%
78.5%	85%	88%	68%	84%	69%	77%
83.8%	87%	89%	85%	81%	75%	86%
86.8%	87%	95%	83%	91%	89%	76%
73.3%	76%	78%	80%	70%	59%	77%
74.8%	74%	78%	71%	75%	76%	75%
47.3%	38%	45%	42%	53%	53%	53%