Who leads the XNLI benchmark?

GPT-4 currently leads XNLI with a score of 87.4 on Accuracy.

What is the state-of-the-art score on XNLI?

The state-of-the-art result on XNLI is 87.4 (Accuracy), achieved by GPT-4 as of 2023.

How many models are tracked on XNLI?

Codesota tracks 3 models on XNLI.

When was the XNLI leaderboard last updated?

The XNLI leaderboard on Codesota includes results through 2023, with the earliest tracked result from 2019.

Codesota · Benchmark · XNLIHome/Leaderboards/XNLI

Unknown

XNLI.

Name: XNLI Benchmark Results
Creator: Unknown
Published: 2019-01-01
License: https://creativecommons.org/licenses/by/4.0/

Cross-lingual natural language inference across 15 languages

Paper ↗Leaderboard ↓

§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

Accuracy

Accuracy is the reported evaluation metric for XNLI. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Accuracyverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	GPT-4 GPT-4 average XNLI accuracy (15 languages). From GPT-4 Technical Report and cross-lingual evaluation studies.	verified	87.4	2023	Source ↗	Looks wrong?
02	XLM-RoBERTa-large XLM-RoBERTa-large XNLI avg accuracy (15 languages). State-of-the-art at publication. From Table 3.	verified	83.6	2019	Source ↗	Looks wrong?
03	mDeBERTa-v3-base mDeBERTa-v3-base average XNLI accuracy across 15 languages. From HF model card.	verified	80.8	2022	Source ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards