Who leads the CodeXGLUE Code-to-Text (Python) benchmark?

CodeT5-base currently leads CodeXGLUE Code-to-Text (Python) with a score of 20.01 on bleu.

What is the state-of-the-art score on CodeXGLUE Code-to-Text (Python)?

The state-of-the-art result on CodeXGLUE Code-to-Text (Python) is 20.01 (bleu), achieved by CodeT5-base as of 2026.

How many models are tracked on CodeXGLUE Code-to-Text (Python)?

Codesota tracks 3 models on CodeXGLUE Code-to-Text (Python).

When was the CodeXGLUE Code-to-Text (Python) leaderboard last updated?

The CodeXGLUE Code-to-Text (Python) leaderboard on Codesota includes results through 2026.

Codesota · Computer Code · Code Summarization · CodeXGLUE Code-to-Text (Python)Tasks/Computer Code/Code Summarization

Code Summarization · benchmark dataset · 2021 · EN

CodeXGLUE Code-to-Text Python subset.

Name: CodeXGLUE Code-to-Text Python subset Benchmark Results
Creator: Codesota
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

Python subset of CodeXGLUE Code-to-Text: generate natural-language docstrings/comments from Python function bodies. Derived from CodeSearchNet. Evaluated with smoothed BLEU-4.

Paper ↗Submit a result ↵

§ 01 · Leaderboard

Best published scores.

3 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary: bleu · higher is better

bleu· primary

3 rows

#	Model	Org	Submitted	Paper / code	bleu
01	CodeT5-baseOSS	Salesforce	Apr 2026	editorial	20.01
02	PLBARTOSS	UCLA / Columbia	Apr 2026	editorial	19.30
03	CodeBERTOSS	Microsoft	Apr 2026	editorial	19.06

Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.

§ 03 · Progress

1 steps
of state of the art.

Each row below marks a model that broke the previous record on bleu. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · bleu

Apr 5, 2026CodeT5-baseSalesforce20.01

Fig 3 · SOTA-setting models only. 1 entries span Apr 2026 → Apr 2026.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide

What a submission needs

01A public checkpoint or API endpoint
02A reproduction script with frozen commit + seed
03Declared evaluation environment (Python, deps)
04One row per metric declared by this dataset
05A contact so we can follow up on discrepancies

CodeXGLUE Code-to-Text Python subset.

Best published scores.

1 stepsof state of the art.

Have a score that beatsthis table?

1 steps
of state of the art.

Have a score that beats
this table?