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%3Abangladesh B2 - Run 2afe1b9...

Global Dialogues GD4 - Bangladesh (batch 2)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Mathematics & Statistics

General Knowledge

Southeast Asia (SEA)

Best Models (Coverage)

1.Claude Haiku 4.5
71.1%
2.Gemini 2.5 Flash
70.7%
3.GPT 4.1 Mini
69.8%
4.GPT 4o Mini
68.4%
5.GPT 4.1 Nano
62.7%

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 71.1%	2nd 70.7%	6th 54.4%	3rd 69.8%	5th 62.7%	4th 68.4%
65.0%		77%		45%	68%	67%	68%
70.8%		81%	80%	49%	77%	67%	71%
65.3%		72%	69%	49%	72%	68%	62%
72.0%		61%	78%	60%	83%	76%	74%
83.7%		85%	82%	76%	88%	81%	90%
55.7%		61%	59%	52%	61%	42%	59%
53.3%		62%	63%	47%	51%	42%	55%
69.2%		68%	68%	69%	71%	63%	76%
63.8%		75%	74%	41%	63%	62%	68%
62.0%		69%	63%	56%	64%	59%	61%