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 C5 Dtef Global Dialogues Gd4 Religion%3Ai Do Not Identify With Any Religious Group Or Faith C5 - Run c1c5bf9...

Global Dialogues GD4 - I do not identify with any religious group or faith (5 context Qs)

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

Reasoning

Instruction Following & Prompt Adherence

AI Safety & Robustness

Best Models (Coverage)

1.Gemini 2.5 Flash
81.6%
2.GPT 4.1 Mini
81.4%
3.Claude Haiku 4.5
81.3%
4.GPT 4o Mini
76.9%
5.GPT 4.1 Nano
74.2%

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	3rd 81.3%	1st 81.6%	- -	2nd 81.4%	5th 74.2%	4th 76.9%
67.6%	76%	71%		66%	62%	63%
70.6%	70%	91%		65%	64%	63%
78.2%	73%	81%		84%	77%	76%
82.6%	90%	79%		76%	84%	84%
62.6%	71%	70%		61%	55%	56%
85.4%	84%	88%		84%	83%	88%
71.6%	90%	81%		70%	56%	61%
78.2%	81%	60%		82%	84%	84%
82.6%	91%	79%		90%	76%	77%
80.2%	86%	64%		85%	89%	77%
84.0%	89%	82%		85%	81%	83%
78.0%	90%	84%		82%	53%	81%
81.6%	85%	80%		83%	78%	82%
60.4%	81%	56%		73%	36%	56%
62.0%	56%	52%		65%	69%	68%
74.2%	89%	84%		81%	45%	72%
82.2%	78%	88%		83%	88%	74%
89.0%	88%	92%		92%	83%	90%
84.4%	92%	91%		87%	69%	83%
87.0%	93%	79%		86%	84%	93%
86.4%	86%	87%		91%	77%	91%
90.8%	89%	96%		92%	89%	88%
77.8%	79%	88%		77%	67%	78%
56.4%	66%	65%		53%	53%	45%
72.8%	78%	83%		65%	71%	67%
87.4%	91%	81%		86%	88%	91%
86.2%	77%	92%		92%	88%	82%
87.2%	94%	80%		86%	91%	85%
79.2%	82%	88%		80%	75%	71%
85.2%	90%	84%		85%	86%	81%
85.2%	93%	73%		86%	88%	86%
69.0%	48%	66%		76%	77%	78%
83.8%	90%	93%		85%	81%	70%
67.2%	71%	87%		67%	57%	54%
80.6%	90%	74%		78%	75%	86%
83.6%	87%	78%		86%	82%	85%
80.6%	78%	79%		86%	80%	80%
79.8%	83%	83%		84%	68%	81%
85.2%	89%	79%		90%	89%	79%
75.0%	65%	71%		83%	76%	80%
82.8%	90%	82%		90%	75%	77%
77.8%	87%	75%		80%	74%	73%
73.8%	79%	74%		73%	83%	60%
75.2%	78%	88%		63%	81%	66%
86.8%	92%	84%		88%	85%	85%
79.4%	76%	85%		88%	74%	74%
83.8%	84%	89%		87%	80%	79%
91.4%	92%	90%		92%	91%	92%
88.2%	90%	81%		93%	92%	85%
83.0%	90%	88%		88%	65%	84%
81.6%	91%	83%		83%	71%	80%
63.6%	59%	83%		60%	57%	59%
84.4%	90%	92%		85%	72%	83%
64.4%	69%	71%		52%	71%	59%
85.8%	83%	78%		88%	90%	90%
83.2%	89%	91%		88%	83%	65%
48.6%	41%	61%		53%	44%	44%
87.0%	89%	87%		92%	77%	90%
62.4%	63%	88%		61%	46%	54%
73.8%	75%	82%		75%	66%	71%
71.4%	83%	51%		88%	67%	68%
75.0%	86%	73%		67%	77%	72%
88.4%	88%	91%		94%	86%	83%
86.2%	87%	88%		88%	81%	87%
84.8%	80%	91%		87%	80%	86%
79.6%	89%	79%		88%	85%	57%
76.4%	85%	92%		74%	80%	51%
76.4%	83%	74%		85%	65%	75%
79.6%	74%	84%		80%	86%	74%
88.8%	88%	93%		82%	93%	88%
88.2%	86%	87%		83%	90%	95%
83.6%	89%	73%		94%	83%	79%
87.4%	91%	88%		94%	80%	84%
62.8%	59%	76%		63%	55%	61%
76.8%	73%	86%		84%	65%	76%
78.4%	72%	83%		82%	74%	81%
81.4%	85%	84%		81%	74%	83%
92.6%	94%	96%		94%	90%	89%
81.6%	81%	83%		85%	82%	77%
80.6%	84%	79%		84%	74%	82%
88.8%	87%	97%		82%	95%	83%
83.2%	93%	91%		87%	53%	92%
74.0%	75%	74%		78%	71%	72%
87.2%	85%	88%		87%	88%	88%
82.4%	81%	84%		84%	78%	85%
83.2%	85%	85%		85%	79%	82%
71.4%	67%	77%		76%	64%	73%
84.4%	91%	85%		84%	70%	92%
66.4%	70%	93%		69%	36%	64%
83.2%	92%	79%		91%	70%	84%
77.0%	75%	83%		79%	74%	74%
65.8%	56%	68%		70%	62%	73%
76.4%	94%	55%		80%	60%	93%
83.0%	87%	85%		88%	69%	86%
69.6%	72%	73%		66%	66%	71%
80.4%	77%	77%		87%	76%	85%
75.2%	84%	76%		79%	68%	69%
79.4%	70%	74%		88%	89%	76%
74.8%	79%	92%		79%	57%	67%
81.2%	85%	90%		87%	63%	81%
66.0%	65%	62%		67%	66%	70%
83.8%	83%	82%		88%	88%	78%
90.6%	90%	94%		87%	91%	91%
81.6%	82%	76%		86%	80%	84%
87.4%	96%	92%		95%	66%	88%
83.2%	62%	94%		90%	92%	78%
64.8%	80%	85%		68%	45%	46%
68.4%	69%	84%		72%	57%	60%
70.0%	66%	77%		73%	56%	78%
81.0%	89%	83%		92%	79%	62%
86.0%	86%	88%		85%	84%	87%
86.8%	83%	92%		93%	77%	89%
84.2%	80%	84%		87%	89%	81%
85.4%	86%	84%		92%	80%	85%
85.4%	80%	96%		90%	75%	86%
83.8%	82%	90%		83%	78%	86%