mteb/leaderboard · Discussions

#133 opened 4 months ago by

cheebw1

New model and mteb leaderboard refresh request

#129 opened 5 months ago by

lvkaokao

New Embedding Models | Apply for refershing the results

Omartificial-Intelligence-Space

#128 opened 5 months ago by

New SFR-Embedding model, Apply for refreshing the results

#127 opened 5 months ago by

yliu279

New GTE model, Apply for refreshing the results

#126 opened 5 months ago by

thenlper

New model and mteb leaderboard refresh request

#117 opened 6 months ago by

nada5

Adding w601sxs/b1ade-embed to the leaderboard

8

#114 opened 6 months ago by

w601sxs

add german mteb overview tab

#113 opened 6 months ago by

aari1995

New C-MTEB Submission Apply for refreshing the results

#112 opened 6 months ago by

shhy1995

i want Hugging Face models that focus on interpreting images and generate a 2-3 line summary based on them.

#107 opened 6 months ago by

ashutosh432

Add German part added in MTEB

8

#87 opened 8 months ago by

aari1995

Can we publish MTEB results to leaderboard for a subset of tasks only?

3

#86 opened 8 months ago by

MichaelKarpe

Machine readable Leaderboard?

#85 opened 8 months ago by

adirendu

New C-MTEB SOTA! Apply for refreshing the results

#84 opened 8 months ago by

aspire

Language distribution in MTEB

#83 opened 8 months ago by

maiia-bocharova

MultiLongDocRetrieval dataset failed to load

#82 opened 8 months ago by

sentosa

When is the leaderboard updated for new models that are uploaded?

#75 opened 9 months ago by

tanmaylaud

Add BGE-M3

#73 opened 9 months ago by

sam-gab

What does `Refresh` functionality do after clicking?

#72 opened 9 months ago by

zhiminy

New Sub-GB SOTA, request for leaderboard refresh

#71 opened 9 months ago by

avsolatorio

incomplete evaluation results

#69 opened 10 months ago by

yin2024

New SOTA! Apply for refreshing the results

9

#64 opened 10 months ago by

memray

New SOTA! Apply for refreshing the results

#62 opened 10 months ago by

mixed-nlp

Why does Spanish is not showed in the leaderboard

#61 opened 10 months ago by

Jowito2000

How to push custom model

#60 opened 10 months ago by

mirth

Runtime error

#57 opened 11 months ago by

zhiminy

Any manner to retrieve the leaderboard results as csv file?

#56 opened 11 months ago by

zhiminy

New SOTA! Apply for refreshing the results

7

#55 opened 11 months ago by

stanpcf

Set height and add model search

#54 opened 11 months ago by

do-me

New SOTA! Apply for refreshing the results

#53 opened 11 months ago by

SeanLee97

Use mteb.info while the space is down

#51 opened 12 months ago by

dhruv-anand-aintech

🚩 Report: Not working

#50 opened 12 months ago by

AlanFeder

Add model size to all tabs

3

#49 opened 12 months ago by

do-me

Add similarity measure used for each model evaluation

7

#44 opened about 1 year ago by

sjrhuschlee

CQADupstackRetrieval evaluation inquiry

#41 opened about 1 year ago by

Izarel

Only allow 1 instance of a particular model name to be in the list.

#40 opened about 1 year ago by

dhruv-anand-aintech

🚩 Report: Not working

#38 opened about 1 year ago by

YulianLee

Restart space to add new models

13

#36 opened about 1 year ago by

zeroshot

Can a private model be added to the leaderboard?

#29 opened about 1 year ago by

Xinyiqin

Restart the space for new models

7

#28 opened about 1 year ago by

infgrad

cannot refresh the leaderboard space

#27 opened about 1 year ago by

Jinkin

Restart space for MTEB leaderboard

3

#26 opened about 1 year ago by

willathum

Benchmark the text embedding models

#25 opened about 1 year ago by

Shimin

Benchmark the latest `SONAR` models from Meta AI

#24 opened about 1 year ago by

reach-vb

Which task is most similar to the average? An analysis via the Kendrall Tau coeffcient

#23 opened about 1 year ago by

varun4

Why no open source llama/orca/platypus submissions?

#22 opened about 1 year ago by

lewington

Multi-language Overall Score

#21 opened about 1 year ago by

loretoparisi

unfair comparison

#20 opened over 1 year ago by

raulcarlomagno

SGPT models sequence length