DTeval

A Collective Intelligence Project

Demographics Findings Experiments

Loading blueprint versions...

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

A Collective Intelligence Project

View App on GitHub|View Eval Blueprints on GitHub|

Loading run instances...

Please wait while we find all executions for this version.

DTEF

Global Dialogues GD4 - 36-45 [indiv] (73 ctx) [first-person]

Run: bcc4ddafb30cb554

Instances for Run Label: bcc4ddafb30cb554 (Blueprint: Global Dialogues GD4 - 36-45 [indiv] (73 ctx) [first-person])

DTEF [indiv]: Predict individual answers for 36-45 (10 participants). Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Individual Answer

Global Dialogues Gd4

Individual Context Format

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Social interaction

Knowledge, learning and memory

Back to All Runs for Blueprint: Global Dialogues GD4 - 36-45 [indiv] (73 ctx) [first-person]

Showing all recorded executions for Run Label bcc4ddafb30cb554.

Executed:

Filename: bcc4ddafb30cb554_2026-03-23T22-16-17-449Z_comparison.json

Avg. Hybrid Score

35.7%

Model Variants

7

Test Cases

710

Executed:

Filename: bcc4ddafb30cb554_2026-03-16T21-53-43-609Z_comparison.json

Avg. Hybrid Score

35.5%

Model Variants

7

Test Cases

710

Executed:

Filename: bcc4ddafb30cb554_2026-03-09T21-45-43-621Z_comparison.json

Avg. Hybrid Score

35.9%

Model Variants

7

Test Cases

710

Executed:

Filename: bcc4ddafb30cb554_2026-03-02T21-14-13-818Z_comparison.json

Avg. Hybrid Score

35.9%

Model Variants

7

Test Cases

710