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%3Aislam B2 - Run b9d8fb5...

Global Dialogues GD3 - Islam (batch 2)

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

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

General Knowledge

Efficiency & Succinctness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude Haiku 4.5
79.2%
2.Gemini 2.5 Flash
78.7%
3.GPT 4o Mini
76.0%
4.GPT 4.1 Mini
74.6%
5.GPT 4.1 Nano
73.3%

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		1st 79.2%	2nd 78.7%	6th 63.9%	4th 74.6%	5th 73.3%	3rd 76.0%
55.5%		66%	59%	46%	54%	43%	65%
72.7%		75%	76%	55%	73%	85%	72%
84.5%		90%	86%	84%	85%	77%	85%
76.5%		85%	78%	61%	80%	71%	84%
74.5%		76%	82%	72%	70%	71%	76%
82.8%		91%	87%	73%	85%	81%	80%
75.2%		74%	71%	75%	84%	73%	74%
79.0%		82%	84%	64%	81%	84%	79%
73.5%		79%	84%	56%	70%	73%	79%
68.7%		74%	80%	53%	64%	75%	66%