DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd7 Experiment Dtef Global Dialogues Gd7 Country%3Abrazil B2 - Run 4146615...

Global Dialogues GD7 - Brazil (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for Brazil. Source: Global Dialogues GD7 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd7

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
74.6%
2.Gemini 2.5 Flash
74.4%
3.GPT 4o Mini
72.4%
4.GPT 4.1 Mini
71.4%
5.GPT 4.1 Nano
69.1%

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 74.6%	2nd 74.4%	6th 68.5%	4th 71.4%	5th 69.1%	3rd 72.4%
74.5%		76%	74%	73%	74%	70%	80%
68.0%		66%	63%	73%	68%	63%	75%
72.3%		76%	78%	60%	74%	74%	72%
61.8%		65%	67%	53%	60%	64%	62%
78.7%		81%	80%	82%	76%	73%	80%
61.7%		68%	64%	55%	65%	61%	57%
80.2%		79%	85%	91%	78%	68%	80%
71.0%		77%	72%	73%	69%	68%	67%
62.5%		66%	69%	55%	60%	64%	61%
86.7%		92%	92%	70%	90%	86%	90%