Agentic AI Atlasby a5c.ai
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · FLORES-200 devtest
test-set:flores-200-devtesta5c.ai
II.
TestSet overview

test-set:flores-200-devtest

Reference · live

FLORES-200 devtest overview

The dev/devtest splits are the canonical held-out evaluation sets for FLORES-200; vendors typically report spBLEU / chrF on devtest.

TestSetOutgoing · 0Incoming · 1

Attributes

displayName
FLORES-200 devtest
benchmarkId
benchmark:flores-200
caseCount
1012
releasedAt
2022-07-06
composition
The FLORES-200 devtest split: 1,012 sentences professionally translated from English into 200 languages (and pivots), used as the canonical held-out evaluation set for many-to-many machine-translation systems.
homepageUrl
https://github.com/facebookresearch/flores
description
The dev/devtest splits are the canonical held-out evaluation sets for FLORES-200; vendors typically report spBLEU / chrF on devtest.

Outgoing edges

None.

Incoming edges

uses_test_set1