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 Country%3Abangladesh B2 - Run a409cff...

Global Dialogues GD3 - Bangladesh (batch 2)

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

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

General Knowledge

Economics & Finance

Political Science

Sociology & Anthropology

AI Safety & Robustness

Best Models (Coverage)

1.Gemini 2.5 Flash
72.5%
2.Claude Haiku 4.5
70.4%
3.GPT 4o Mini
67.1%
4.GPT 4.1 Mini
65.4%
5.GPT 4.1 Nano
60.9%

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 70.4%	1st 72.5%	6th 47.3%	4th 65.4%	5th 60.9%	3rd 67.1%
44.7%		41%	54%	33%	43%	43%	54%
73.3%		80%	85%	61%	80%	55%	79%
64.5%		75%	70%	49%	70%	56%	67%
62.7%		70%	68%	49%	67%	56%	66%
61.5%		65%	70%	47%	67%	61%	59%
79.7%		84%	87%	72%	74%	79%	82%
70.8%		74%	73%	72%	68%	67%	71%
67.7%		74%	75%	47%	69%	68%	73%
64.0%		79%	79%	19%	69%	71%	67%
50.5%		62%	64%	24%	47%	53%	53%