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%3Akenya B2 - Run 35fbb80...

Global Dialogues GD3 - Kenya (batch 2)

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

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

General Knowledge

AI Bias & Fairness

Best Models (Coverage)

1.Gemini 2.5 Flash
69.7%
2.Claude Haiku 4.5
69.6%
3.GPT 4.1 Nano
65.8%
4.GPT 4o Mini
65.1%
5.GPT 4.1 Mini
64.2%

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 69.6%	1st 69.7%	6th 46.9%	5th 64.2%	3rd 65.8%	4th 65.1%
33.8%		38%	43%	25%	29%	28%	40%
60.2%		66%	65%	43%	56%	62%	69%
80.3%		84%	82%	64%	85%	87%	80%
70.7%		80%	72%	46%	76%	74%	76%
59.0%		60%	64%	56%	62%	56%	56%
75.0%		81%	76%	63%	77%	84%	69%
70.7%		70%	77%	72%	72%	68%	65%
69.2%		75%	74%	50%	71%	74%	71%
63.2%		75%	78%	27%	65%	63%	71%
53.5%		67%	66%	23%	49%	62%	54%