DTeval

Loading analysis results...

Please wait while we prepare the detailed comparison.

Loading blueprint versions...

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

Analysis: Gd4 Individual First Person Blueprints Individual First Person Dtef Global Dialogues Gd4 Country%3Apoland Firstperson Indiv Individual - Run e28baea...

Global Dialogues GD4 - Poland [indiv] (73 ctx) [first-person]

DTEF [indiv]: Predict individual answers for Poland (10 participants). Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

Best Models (Coverage)

1.Gemma 3 12b It
39.8%
2.GPT 4.1 Nano
26.7%
3.GPT 4o Mini
16.1%
4.Claude Haiku 4.5
13.2%
5.Gemini 2.5 Flash
12.1%

View Blueprint

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

	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 13.2%	5th 12.1%	1st 39.8%	6th 7.7%	2nd 26.7%	3rd 16.1%
46.2%	16%	78%	97%	0%	86%	0%
0.0%	0%	0%	0%	0%	0%	0%
10.8%	0%	0%	0%	0%	65%	0%
59.2%	95%	0%	84%	89%	9%	78%
61.8%	88%	32%	84%	78%	0%	89%
10.4%		0%	20%	0%	7%	25%
3.3%	0%	0%	12%	0%	0%	8%
2.3%	0%	0%	0%	0%	0%	14%
7.8%	0%	0%	39%	0%	0%	8%
13.8%	0%	6%	0%	0%	77%	0%
2.8%	17%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
2.7%	0%	0%	0%	0%	6%	10%
14.8%	1%	0%	84%	0%	4%	0%
14.8%	0%	0%	0%	0%	89%	0%
18.8%	0%	0%	81%	0%	32%	0%
13.5%	0%	0%	81%	0%	0%	0%
59.2%	66%	53%	55%	60%	43%	78%
14.2%	0%	0%	77%	0%	8%	0%
41.8%	0%	0%	97%	0%	65%	89%
17.8%	53%	54%	0%	0%	0%	0%
0.0%	0%	0%		0%	0%	0%
12.5%	0%	0%	0%	0%	65%	10%
16.2%	6%	0%	84%	0%	7%	0%
13.0%	0%	46%	0%	0%	32%	0%
33.3%	0%	54%	81%	0%	65%	0%
13.5%	0%	0%	81%	0%	0%	0%
22.5%	0%	0%	55%	6%	74%	0%
8.7%	0%	0%	0%	0%	52%	0%
36.3%	2%	54%	97%	0%	65%	0%
0.0%	0%	0%	0%	0%	0%	0%
10.0%	0%	0%	60%	0%	0%	0%
3.0%	0%	0%	3%	0%	5%	10%
64.2%	86%	54%	84%	79%	14%	68%
74.8%	81%	52%	84%	66%	88%	78%
2.3%	0%	14%	0%	0%	0%	0%
20.5%	16%	14%	0%	3%	65%	25%
22.8%	0%	14%	55%	6%	62%	0%
12.0%	23%	14%	0%	0%	35%	0%
9.0%		0%	39%	0%	6%	0%
19.7%	52%	0%	0%	0%	0%	66%
0.0%	0%	0%	0%	0%	0%	0%
11.3%	0%	68%	0%	0%	0%	0%
28.3%	7%	0%	84%	0%	1%	78%
30.5%	0%	0%	97%	0%	86%	0%
28.5%	15%	0%	72%	0%	32%	52%
1.3%	0%	0%	0%	0%	0%	8%
1.5%	9%	0%	0%	0%	0%	0%
16.0%	0%	0%	71%	0%	25%	0%
28.0%	0%	0%	92%	0%	66%	10%