DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd3 Experiment Dtef Global Dialogues Gd3 Religion%3Aother Religious Group B2 - Run 7cbe12a...

Global Dialogues GD3 - Other religious group (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for Other religious group. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.GPT 4o Mini
77.6%
2.Claude Haiku 4.5
77.1%
3.GPT 4.1 Mini
76.5%
4.Gemini 2.5 Flash
76.5%
5.GPT 4.1 Nano
71.7%

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 77.1%	3rd 76.5%	6th 66.7%	3rd 76.5%	5th 71.7%	1st 77.6%
56.0%		69%	63%	44%	60%	34%	66%
74.7%		74%	73%	61%	74%	83%	83%
86.3%		85%	88%	83%	87%	87%	88%
74.2%		80%	76%	65%	80%	64%	80%
79.0%		78%	85%	75%	83%	73%	80%
76.7%		79%	81%	75%	75%	72%	78%
75.7%		71%	69%	80%	78%	81%	75%
79.8%		83%	83%	71%	81%	80%	81%
71.7%		76%	72%	59%	77%	72%	74%
69.5%		76%	75%	54%	70%	71%	71%