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%3Akorea South B2 - Run 4050eb3...

Global Dialogues GD4 - Korea South (batch 2)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.Gemini 2.5 Flash
69.2%
2.Claude Haiku 4.5
66.9%
3.GPT 4o Mini
66.8%
4.GPT 4.1 Mini
65.7%
5.Gemma 3 12b It
62.0%

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 66.9%	1st 69.2%	5th 62.0%	4th 65.7%	6th 53.4%	3rd 66.8%
56.5%		53%	60%	56%	60%	49%	61%
69.5%		66%	75%	71%	71%	63%	71%
69.8%		72%	73%	67%	70%	63%	74%
44.3%		47%	64%	42%	42%	20%	51%
65.7%		66%	66%	59%	68%	67%	68%
56.8%		72%	67%	49%	66%	31%	56%
65.2%		75%	71%	65%	66%	44%	70%
67.7%		63%	63%	68%	73%	61%	78%
74.8%		81%	82%	72%	71%	73%	70%
69.7%		74%	71%	71%	70%	63%	69%