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 AgeGroup%3A36 45 B2 - Run fb0828f...

Global Dialogues GD4 - 36-45 (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for 36-45. 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

Best Models (Coverage)

1.GPT 4o Mini
82.5%
2.Gemini 2.5 Flash
81.9%
3.GPT 4.1 Mini
80.8%
4.Claude Haiku 4.5
79.8%
5.Gemma 3 12b It
76.4%

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		4th 79.8%	2nd 81.9%	5th 76.4%	3rd 80.8%	6th 75.7%	1st 82.5%
82.3%		78%	84%	85%	85%	76%	86%
87.2%		93%	87%	76%	93%	86%	88%
83.7%		84%	89%	78%	85%	80%	86%
62.2%		56%	68%	59%	67%	49%	74%
82.2%		80%	87%	78%	78%	83%	87%
72.8%		82%	76%	73%	76%	58%	72%
76.5%		74%	77%	73%	76%	79%	80%
81.8%		79%	81%	73%	87%	82%	89%
76.7%		77%	78%	76%	74%	80%	75%
89.8%		95%	92%	93%	87%	84%	88%