whatmodel.sh / LaMDA 422M (pre-trained)

LaMDA 422M (pre-trained)

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

LaMDA 422M (pre-trained) is a closed-weights language model from Google, released January 2022. Its published size is 0.422B parameters. Licence: proprietary.

Catalogue identity notes

Smaller pre-trained LaMDA model evaluated by Google in Wei et al. (arXiv:2201.11903v6: 'LaMDA ... which has models of 422M, 2B, 8B, 68B, and 137B parameters'; table label '420M'). Released date is the LaMDA paper month (the LaMDA paper itself describes sizes 2B-137B). Never released. Comparison-only.

Model information sources

Release date ↗

0.9±3.0comparison only: no current run option verifiedfrom 9 benchmark results across 1 source

Score within the LMArena (text) comparison set only.

$ how it compares

The LLMs ranked either side of LaMDA 422M (pre-trained), out of 877 with a score, then more from Google.

#modelscorewhereRAMreleased
866GPT-3 text-ada-001 OpenAI1±3comparison only2022-01
867OPT-350M Meta1±1local~2.2GB2022-05
868LaMDA 422M (pre-trained) Google1±3never released2022-01
869StableLM-Base-Alpha 3B Stability AI1±2local~17GB2023-04
870BLOOM 560M BigScience0±1local~2.1GB2022-07
more from Google
11Gemini 4 Argon Google80±1api $4.00/M2026-09
26Gemini 3.8 Flash Google76±1api $1.50/M2026-09
34Gemini 3.7 Flash Google75±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

math▃▂▃▆█▇▅▇▃▁▁▁ #521 of 523 * · 4.5% of its score · 1 test

Trails GPT-2 Small (124M), GPT-Neo 125M, OPT-125M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab0.4% ✎█·▅▃▃▃·▃·▃▃▅ beats 0/12easy · avg 67%▇▇ 4.5%sharp · too hard for it
other tests8 not in a task · 92% of its score
testresultvs the others in its rundifficultycountswhy
MAWPS (CoT-paper union) lab0.9% ✎▅▃█···▅·▃▃▃▅ beats 0/12very easy · avg 94%▇▇▇▇▇▇▇▇▇▇▇▇ 29%sharp · too hard for it
ASDiv lab0.8% ✎▅▃▃▅··▃▃·▃▃█ beats 0/12easy · avg 83%▇▇▇▇▇▇▇▇▇ 22%sharp · too hard for it
SVAMP lab1.6% ✎▃▅█···▅·▃▃▃▅ beats 1/12easy · avg 82%▇▇▇▇▇▇ 15%sharp · too hard for it
BIG-bench Date Understanding lab1.9% ✎▃·▅·▅▃▅·▃▃·█ beats 0/12medium · avg 52%▇▇▇▇▇▇ 14%too hard for it
StrategyQA lab46.4% ✎█·····▅▃▃▅▃█ beats 0/12medium · avg 70%▇▇ 5.1%too hard for it
BIG-bench Sports Understanding lab50.0% ✎█·····▃·▁·▄▁ beats 2/12medium · avg 81%▇ 3.0%sharp · too hard for it
CommonsenseQA lab20.1% ✎█······▁·▁▁▃ beats 2/12easy · avg 87%▇ 2.9%sharp · too hard for it
AQuA-RAT lab8.3% ✎█▁·▁▁·····▂▁ beats 3/12medium · avg 48%▇ 0.3%sharp · too hard for it

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Chain-of-Thought Prompting El… 96%

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
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — authors' own runs · lab-reported9CC BY 4.0
prior · pull toward the middle
weighted average= 0.9

$ 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