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%3Achina B2 - Run 0ddd06b...

Global Dialogues GD3 - China (batch 2)

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

TAGS:

Global Dialogues Gd3

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Gemini 2.5 Flash
73.7%
2.Claude Haiku 4.5
71.2%
3.GPT 4.1 Mini
69.8%
4.GPT 4o Mini
69.5%
5.GPT 4.1 Nano
67.0%

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 71.2%	1st 73.7%	6th 56.4%	3rd 69.8%	5th 67.0%	4th 69.5%
54.0%		69%	68%	39%	55%	33%	60%
72.8%		70%	71%	61%	77%	79%	79%
73.3%		70%	65%	79%	72%	72%	82%
67.5%		70%	74%	53%	76%	56%	76%
68.5%		63%	84%	62%	68%	75%	59%
80.0%		80%	85%	73%	83%	80%	79%
70.2%		74%	71%	62%	74%	76%	64%
65.3%		67%	70%	59%	68%	63%	65%
68.8%		77%	79%	40%	72%	72%	73%
58.8%		72%	70%	36%	53%	64%	58%