Compare the listed model data for BART Large CNN by facebook and PEGASUS XSum by google. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
BART Large CNN: 1024 tokens; PEGASUS XSum: 1024 tokens. The listed context-window values are equal. BART Large CNN is listed for no specific capability flags; PEGASUS XSum is listed for no specific capability flags. Shared catalog benchmark entries: No shared benchmark labels are listed in these model records. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
The listed context windows are 1024 tokens and 1024 tokens; the larger is 1× the smaller.
No shared benchmark labels are present in both catalog records.
The first listed parameter quantities are 400M and 568M; the larger quantity is 1.42× the smaller. Total and active MoE parameters are not directly equivalent.
The catalog release dates are October 2019 and December 2019, about 2 months apart at the precision supplied.
Cost example: 1M input and 1M output tokens
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose BART Large CNN if…
Choose BART Large CNN when your task aligns with catalog-listed uses or strengths such as News article summarization APIs, Content aggregation pipelines, Short document summarization under 1000 tokens, Purpose-built for news summarization — state-of-the-art on CNN/DailyMail at release.
Choose PEGASUS XSum if…
Choose PEGASUS XSum when your task aligns with catalog-listed uses or strengths such as News headline generation, Social media summary from articles, XSum benchmark leader at release — highly abstractive single-sentence summaries, Novel pretraining for summarization: gap-sentence generation.
Feature Comparison — BART Large CNN vs PEGASUS XSum
Catalog specifications for BART Large CNN and PEGASUS XSum
Specification
BART Large CNN
PEGASUS XSum
Provider
facebook
google
Parameters
400M
568M
Context window
1024 tokens
1024 tokens
Maximum output
Not listed
Not listed
Catalog pricing
MIT — free
Apache 2.0 — free
Listed input/output cost per 1M tokens
Separate numeric input/output rates not listed
Separate numeric input/output rates not listed
License
MIT
Apache 2.0
Coding support
Not listed
Not listed
Reasoning support
Not listed
Not listed
Vision input
Not listed
Not listed
Multimodal
Not listed
Not listed
Open weights
Yes
Yes
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between BART Large CNN and PEGASUS XSum?
BART Large CNN: 1024 tokens; PEGASUS XSum: 1024 tokens. The listed context-window values are equal. BART Large CNN is listed for no specific capability flags; PEGASUS XSum is listed for no specific capability flags. Shared catalog benchmark entries: No shared benchmark labels are listed in these model records. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for BART Large CNN and PEGASUS XSum?
No shared benchmark labels are listed in these model records. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
BART Large CNN: 1024 tokens; PEGASUS XSum: 1024 tokens. The listed context-window values are equal.
What are the listed costs per million tokens for BART Large CNN and PEGASUS XSum?
BART Large CNN: Separate numeric input/output rates not listed (MIT — free). PEGASUS XSum: Separate numeric input/output rates not listed (Apache 2.0 — free). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for BART Large CNN and PEGASUS XSum?
The catalog lists BART Large CNN as October 2019 and PEGASUS XSum as December 2019, about 2 months apart at the precision supplied.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between BART Large CNN and PEGASUS XSum?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.
Create your free LITHOVEX account and compare BART Large CNN and PEGASUS XSum on your actual tasks. No credit card, no API key, no subscriptions needed.