Codesota · Models · PEGASUS-LargeGoogle3 results · 1 benchmarks
Model card

PEGASUS-Large.

Googleopen-sourceUnknown paramsTransformer encoder-decoder (gap-sentence generation pre-training)

PEGASUS large model. ICML 2020.

§ 02 · Benchmarks

Every benchmark PEGASUS-Large has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CNN/DailyMailNatural Language Processing · Text Summarizationrouge-221.5%#3/32019-12-18source ↗
02CNN/DailyMailNatural Language Processing · Text Summarizationrouge-144.2%#6/62019-12-18source ↗
03CNN/DailyMailNatural Language Processing · Text Summarizationrouge-l41.1%#6/72019-12-18source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where PEGASUS-Large actually performs.

Natural Language Processing
1
benchmark
avg rank #5.0
§ 04 · Papers

1 paper with results for PEGASUS-Large.

  1. 2019-12-18· Natural Language Processing· 3 results

    PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

§ 05 · Related models

Other Google models scored on Codesota.

Gemini 1.5 Pro
21 results
Gemini 2.5 Pro
16 results
Gemini 3 Pro
Undisclosed params · 13 results
Gemini-3.1-Pro
11 results
Gemma-3-27b
27B params · 11 results
Gemma 3 (27B, IT)
9 results
Gemma-2-27b-it
9 results
gemma-3-12b-it
9 results
§ 06 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.