DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd3 Dtef Global Dialogues Gd3 Country%3Akorea South - Run de19f70...

Global Dialogues GD3 - Korea South

DTEF: Predict response distributions for Korea South. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

General Knowledge

Economics & Finance

Political Science

Sociology & Anthropology

AI Safety & Robustness

Information Ecology & Synthetic Content Proliferation

Best Models (Coverage)

1.Claude Haiku 4.5
75.5%
2.Gemini 2.5 Flash
72.1%
3.GPT 4.1 Mini
71.7%
4.GPT 4o Mini
70.7%
5.GPT 4.1 Nano
67.9%

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 75.5%	2nd 72.1%	- -	3rd 71.7%	5th 67.9%	4th 70.7%
67.6%		73%	65%		70%	65%	65%
67.8%		67%	54%		69%	77%	72%
55.6%		61%	48%		57%	59%	53%
64.0%		63%	57%		60%	61%	79%
74.0%		74%	77%		76%	72%	71%
88.2%		96%	87%		76%	92%	90%
89.6%		96%	84%		92%	88%	88%
68.6%		77%	73%		58%	67%	68%
76.8%		76%	75%		76%	77%	80%
54.0%		58%	56%		58%	49%	49%
82.6%		91%	82%		90%	76%	74%
62.4%		67%	73%		56%	55%	61%
72.6%		81%	79%		74%	57%	72%
90.2%		89%	86%		94%	91%	91%
71.8%		78%	79%		73%	60%	69%
66.4%		72%	68%		70%	61%	61%
57.4%		67%	61%		54%	48%	57%
74.4%		77%	73%		72%	75%	75%
56.2%		59%	55%		54%	60%	53%
82.2%		77%	88%		82%	82%	82%
66.4%		69%	67%		66%	65%	65%
79.0%		73%	84%		74%	83%	81%
86.4%		91%	93%		92%	65%	91%
67.8%		74%	73%		72%	54%	66%
68.2%		67%	76%		60%	74%	64%
69.4%		70%	72%		74%	67%	64%
61.4%		67%	62%		56%	62%	60%
63.6%		69%	73%		61%	57%	58%
56.4%		71%	57%		59%	38%	57%
76.6%		82%	84%		73%	68%	76%
58.6%		66%	61%		54%	54%	58%
86.0%		92%	81%		88%	86%	83%
95.6%		92%	97%		96%	94%	99%
81.2%		90%	65%		88%	75%	88%
72.8%		87%	67%		80%	55%	75%
63.4%		72%	61%		60%	64%	60%
55.6%		61%	58%		49%	53%	57%
70.4%		76%	77%		85%	47%	67%
67.0%		72%	70%		70%	65%	58%
94.2%		98%	87%		93%	100%	93%
68.0%		71%	67%		67%	71%	64%
74.4%		71%	74%		79%	77%	71%
72.2%		68%	73%		74%	73%	73%