DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Experiment Dtef Global Dialogues Gd4 Country%3Amexico B2 - Run 4ce76e7...

Global Dialogues GD4 - Mexico (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for Mexico. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

General Knowledge

Economics & Finance

Political Science

Sociology & Anthropology

AI Safety & Robustness

Information Ecology & Synthetic Content Proliferation

Best Models (Coverage)

1.GPT 4o Mini
64.3%
2.Gemma 3 12b It
63.9%
3.Gemini 2.5 Flash
63.4%
4.GPT 4.1 Mini
62.8%
5.Claude Haiku 4.5
61.9%

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		5th 61.9%	3rd 63.4%	2nd 63.9%	4th 62.8%	6th 59.8%	1st 64.3%
67.2%		63%	65%	65%	68%	74%	68%
58.8%		53%	58%	77%	55%	47%	63%
71.5%		73%	67%	74%	69%	74%	72%
41.7%		39%	45%	44%	40%	37%	45%
66.5%		68%	72%	61%	63%	68%	67%
59.5%		59%	63%	55%	64%	49%	67%
67.2%		73%	67%	60%	70%	67%	66%
61.8%		56%	57%	66%	63%	64%	65%
62.7%		66%	65%	61%	64%	55%	65%
70.0%		69%	75%	76%	72%	63%	65%