DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd6 Experiment Dtef Global Dialogues Gd6 Religion%3Aislam B2 - Run 0a340f3...

Global Dialogues GD6 - Islam (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for Islam. Source: Global Dialogues GD6 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd6

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Economics & Finance

Political Science

Sociology & Anthropology

AI Safety & Robustness

General Knowledge

Best Models (Coverage)

1.Gemini 2.5 Flash
85.0%
2.Claude Haiku 4.5
84.3%
3.GPT 4.1 Mini
83.1%
4.GPT 4o Mini
82.9%
5.GPT 4.1 Nano
81.9%

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

	Prompts vs. Models	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 84.3%	1st 85.0%	6th 73.7%	3rd 83.1%	5th 81.9%	4th 82.9%
83.8%		83%	90%	82%	89%	76%	83%
75.3%		74%	73%	68%	80%	74%	83%
80.0%		83%	77%	62%	82%	95%	81%
84.5%		91%	88%	68%	84%	90%	86%
83.7%		84%	88%	72%	87%	82%	89%
75.7%		81%	84%	58%	71%	80%	80%
74.2%		79%	82%	64%	74%	76%	70%
82.0%		85%	90%	82%	79%	77%	79%
89.2%		90%	92%	94%	93%	78%	88%
89.8%		93%	86%	87%	92%	91%	90%