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%3Asouth Africa Firstperson Indiv Individual - Run db15fdd...

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

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

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Factual Accuracy & Hallucination

Efficiency & Succinctness

Best Models (Coverage)

1.Gemma 3 12b It
45.2%
2.GPT 4.1 Nano
40.2%
3.Claude Haiku 4.5
39.4%
4.GPT 4o Mini
36.8%
5.Gemini 2.5 Flash
35.9%

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	3rd 39.4%	5th 35.9%	1st 45.2%	6th 33.8%	2nd 40.2%	4th 36.8%
98.3%	99%	100%	100%	97%	97%	97%
86.4%		78%	97%	97%	86%	74%
39.8%	0%	78%	0%	87%	74%	0%
21.0%	0%	52%	0%	0%	74%	0%
41.5%	7%	0%	0%	91%	77%	74%
56.5%	83%	0%	83%	88%	7%	78%
19.7%	0%	32%	0%	0%	86%	0%
24.2%		0%	83%	0%	7%	31%
7.0%	0%	22%	20%	0%	0%	0%
17.5%	0%	31%	0%	0%	74%	0%
90.2%	91%	78%	97%	97%	91%	87%
1.2%	0%	0%	0%	0%	0%	7%
34.2%	63%	52%	0%	7%	77%	6%
46.0%	66%	49%	73%	23%	15%	50%
10.8%	0%	0%	0%	0%	65%	0%
8.3%	0%	0%	0%	3%	47%	0%
60.7%	65%	54%	84%	59%	24%	78%
26.0%	0%	14%	71%	0%	32%	39%
47.2%	19%	54%	0%	88%	64%	58%
11.5%	12%	38%	0%	9%	0%	10%
94.8%	95%	99%	100%	97%	91%	87%
88.8%	98%	78%	100%	97%	86%	74%
42.5%	93%	78%	0%	7%	77%	0%
54.2%	89%	49%	84%	60%	15%	28%
43.3%	88%	88%	0%	0%	78%	6%
52.3%	80%	0%	84%	78%	7%	65%
62.2%	71%	54%	84%	66%	32%	66%
18.3%	0%	36%	0%	0%	74%	0%
54.7%	99%	0%	0%	88%	64%	77%
18.5%	21%	68%	22%	0%	0%	0%
91.2%	97%	78%	100%	97%	91%	84%
15.2%	0%	0%	84%	0%	0%	7%
34.2%	20%	54%	84%	0%	16%	31%
22.5%	16%	32%	39%	0%	16%	32%
19.2%	0%	0%	84%	0%	0%	31%
69.7%	86%	52%	84%	66%	65%	65%
40.0%	0%	54%	84%	0%	24%	78%
0.0%	0%	0%	0%	0%	0%	0%
3.0%	0%	0%	0%	0%	8%	10%
27.0%	27%	32%	58%	0%	15%	30%
87.2%	88%	78%	91%	91%	91%	84%
68.8%	75%	78%	0%	97%	86%	77%
27.8%	53%	23%	84%	0%	0%	7%
1.5%	9%	0%	0%	0%	0%	0%
11.7%	5%	0%	58%	0%	0%	7%
3.0%	0%	3%	9%	6%	0%	0%
41.8%	65%	0%	84%	0%	24%	78%
42.5%	59%	23%	71%	0%	24%	78%
36.3%	22%	0%	35%	88%	22%	51%
12.7%	32%	5%	28%	6%	5%	0%