Directory label
Multilingual: AI benchmarks
A label other catalogs put on entries, not one of the domains on our map. On the map, each entry here sits in the domain its own site or paper leads with.
Work in languages other than English, measuring whether a model's knowledge and skills carry across languages.
- AI benchmarks
- 51
- Shares entries with
- 0 categories
Snapshot 2026-11-05. How categories are built · Where the data comes from
In short
- What are the main multilingual benchmarks?
- MGSM, INCLUDE, MILU, MultiLexNorm++, MMLU-ProX and AfroBench-Lite, among 44 confirmed below.
Only benchmarks use the Multilingual tag: the RL environment directories file their vendors under other categories. Browse all RL environments.
AI benchmarks 51
-
MGSM
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
INCLUDE
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MILU
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MultiLexNorm++
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MMLU-ProX
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
AfroBench-Lite
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
IFMTBench
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
INCLUDE-base-44 European Languages
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
P3B3
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Script Sensitivity
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
NOVA-63
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
PolyMath
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MAXIFE
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
AfroBench
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
SemEval-2026 Task 7
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
BabelJudge
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
BLUEX v2
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Can Large Language Models Understand
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
ChiEngMixBench
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
G-IdiomAlign
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MULTITEXTEDIT
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Not Truly Multilingual
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
OLA: Output Language Alignment in Code-Switched LLM Interactions
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
PersLitEval
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
One Instruction Does Not Fit All
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
AA Global-MMLU-Lite
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
XTREME
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
VWT2k-lite
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
NanoBEIR Multilingual
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MKQA-11
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
WMT26
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
AmharicStoryQA
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Disentangling Language Roles in Multilingual LLM Task Execution
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Evaluating Cross-lingual Knowledge Consistency in Code-Mixed vis-a-vis Indian Languages using IndicKLAR
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
MASSIVE
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
PAWS-X
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
XNLI
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
XTREME-R
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
LatamBoard
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
LexNeo-Bench
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
LLMs Infer Cultural Context but Fail to Apply It When Responding
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
-
Open Multilingual LLM Evaluation Leaderboard
No line from its own site or paper places it in Multilingual yet; the catalog lists it here.
7 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.