DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd6 Experiment Dtef Global Dialogues Gd6 Country%3Apoland B2 - Run 1ccca0d...

Global Dialogues GD6 - Poland (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for Poland. Source: Global Dialogues GD6 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd6

Instruction Following & Prompt Adherence

Efficiency & Succinctness

Factual Accuracy & Hallucination

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
77.4%
2.Gemini 2.5 Flash
77.2%
3.GPT 4o Mini
76.0%
4.GPT 4.1 Mini
74.8%
5.GPT 4.1 Nano
73.1%

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 77.4%	2nd 77.2%	6th 72.4%	4th 74.8%	5th 73.1%	3rd 76.0%
82.0%		81%	84%	86%	78%	82%	81%
74.0%		75%	73%	74%	73%	70%	79%
72.0%		79%	72%	56%	75%	74%	76%
77.3%		78%	78%	77%	76%	70%	85%
76.3%		77%	77%	77%	76%	70%	81%
71.7%		79%	80%	53%	66%	80%	72%
75.7%		82%	80%	69%	81%	69%	73%
82.7%		85%	83%	82%	84%	83%	79%
64.2%		65%	63%	70%	66%	56%	65%
75.7%		73%	82%	80%	73%	77%	69%