whatmodel.sh / Flan-T5 Large

Flan-T5 Large

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Flan-T5 Large is an open-weights language model from Google, released October 2022. Its published size is 0.783B parameters. Licence: apache-2.0.

Catalogue identity notes

Instruction-finetuned T5 v1.1 LM-adapted checkpoint released with Chung et al. 2022.

26.6±1.9#663 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Flan-T5 Large, out of 828 with a score, then more from Google.

#modelscorewhereRAMreleased
762ChatGLM3-6B Zhipu AI (THUDM)27±2local~5.8GB2023-10
763Granite 4.0 H 350M IBM27±1local~1.7GB2025-10
764Flan-T5 Large Google27±2local~4.8GB2022-10
765MPT-7B-Chat MosaicML27±2comparison only2023-05
766Gemma 2B IT Google27±1local~3.1GB2024-02
more from Google
9Gemini 4 Argon (limited preview) Google82±1limited preview2026-09
23Gemini 3.8 Flash Google77±1api $1.50/M2026-09
32Gemini 3.7 Flash Google76±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

math██·█···█···█ #3 of 5 * · 19% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
MGSM lab0.7% ✎▃·▁·▁··▂▄█▄▄ beats 2/26hard · avg 22%▇▇▇▇▇▇▇▇ 19%too hard for it
other tests3 not in a task · 79% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab37.5% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 19/129easy · avg 80%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%sharp
MMLU lab45.1% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 28/183easy · avg 82%▇▇▇▇▇▇▇▇▇▇▇▇ 29%typical
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)81.7% ✎▁▃▂▃▄▄█▆▃▂▂▁ beats 6/140very easy · avg 94%▇▇ 4.9%blunt · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~3.13 GB · from huggingface.co/google (official)
    uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text2text-generation', model='google/flan-t5-large')('Answer the question: what is the capital of France?', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/google ↗

$ how the score was worked out · Scaling Instruction-Finetuned… 93%, Vectara hallucination leaderb… 5%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Scaling Instruction-Finetuned Language Models — authors' own runs · lab-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%CC BY 4.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 5%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 26.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json