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%3Aindia Firstperson Indiv Individual - Run 48f001b...

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

DTEF [indiv]: Predict individual answers for India (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.GPT 4.1 Nano
47.2%
2.Gemma 3 12b It
45.3%
3.GPT 4o Mini
35.7%
4.GPT 4.1 Mini
34.9%
5.Claude Haiku 4.5
34.8%

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	5th 34.8%	6th 33.8%	2nd 45.3%	4th 34.9%	1st 47.2%	3rd 35.7%
0.0%	0%	0%	0%	0%	0%	0%
48.5%	78%	78%	35%	68%	0%	32%
54.3%	0%	78%	0%	97%	77%	74%
91.2%	99%	89%	97%	97%	87%	78%
12.8%	0%	0%	0%	0%	77%	0%
94.8%	99%	100%	100%	97%	86%	87%
29.6%		0%	83%	0%	65%	0%
43.0%	20%	78%	0%	0%	86%	74%
98.8%	100%	100%	100%	99%	97%	97%
46.0%	5%	88%	0%	97%	86%	0%
2.5%	9%	0%	0%	0%	0%	6%
43.5%	23%	0%	84%	78%	24%	52%
28.5%	66%	0%	84%	0%	7%	14%
1.3%	0%	0%	0%	0%	8%	0%
23.8%	20%	26%	0%	20%	77%	0%
3.5%	21%	0%	0%	0%	0%	0%
27.0%	0%	0%	97%	0%	65%	0%
32.2%	52%	53%	0%	0%	88%	0%
90.5%	93%	78%	100%	97%	88%	87%
50.5%	23%	54%	0%	88%	78%	60%
30.2%	42%	0%	58%	66%	7%	8%
63.0%	89%	68%	84%	78%	7%	52%
16.3%	0%	0%	84%	0%	0%	14%
30.8%	0%	0%	97%	0%	88%	0%
31.3%	66%	0%	84%	0%	7%	31%
36.6%		0%	0%	7%	87%	89%
43.8%	0%	0%	97%	0%	71%	95%
30.3%	19%	78%	0%	7%	78%	0%
94.5%	97%	89%	100%	97%	97%	87%
58.5%	72%	53%	0%	88%	78%	60%
21.0%		14%	60%	0%	0%	31%
39.2%	53%	54%	28%	68%	0%	32%
29.0%	1%	68%	84%	0%	7%	14%
61.7%	89%	54%	0%	97%	78%	52%
20.3%	7%	0%	84%	0%	0%	31%
64.7%	80%	79%	0%	91%	78%	60%
1.7%	0%	0%	0%	0%	0%	10%
22.7%	0%	32%	84%	0%	0%	20%
92.5%	95%	88%	100%	97%	88%	87%
0.0%	0%	0%	0%	0%	0%	0%
17.8%		89%	0%	0%	0%	0%
23.0%	14%	0%	84%	0%	15%	25%
21.3%	7%	23%	84%	0%	0%	14%
28.3%	0%	0%	92%	0%	78%	0%
21.5%	23%	0%	0%	20%	78%	8%
34.8%		0%	0%	7%	78%	89%
0.0%	0%	0%	0%	0%	0%	0%
36.7%	8%	0%	83%	0%	78%	51%
90.0%	88%	80%	100%	97%	88%	87%
42.0%	8%	0%	0%	88%	78%	78%