DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Matrix Dtef Global Dialogues Gd4 Country%3Asouth Africa B2 - Run da15116...

Global Dialogues GD4 - South Africa (batch 2)

DTEF: Batched predictions (2 Qs/prompt) for South Africa. 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

Factual Accuracy & Hallucination

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
59.8%
2.Gemini 2.5 Flash
57.9%
3.GPT 4.1 Nano
56.0%
4.GPT 4.1 Mini
54.6%
5.GPT 4o Mini
52.9%

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 59.8%	2nd 57.9%	6th 45.7%	4th 54.6%	3rd 56.0%	5th 52.9%
68.2%		79%	69%	54%	71%	66%	70%
38.5%		42%	44%	21%	36%	57%	31%
53.2%		59%	60%	42%	57%	56%	45%
70.3%		74%	77%	64%	68%	63%	76%
50.3%		57%	49%	43%	45%	56%	52%
55.3%		60%	57%	47%	60%	48%	60%
35.5%		40%	38%	29%	39%	29%	38%
74.2%		79%	81%	74%	70%	71%	70%
46.5%		49%	54%	42%	33%	57%	44%
52.8%		59%	50%	41%	67%	57%	43%