whatmodel.sh / LaMDA 2B (pre-trained)

LaMDA 2B (pre-trained)

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

LaMDA 2B (pre-trained) is a closed-weights language model from Google, released January 2022. Its published size is 2B 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 '2B'). Released date is the LaMDA paper month (the LaMDA paper itself describes sizes 2B-137B). Never released. Comparison-only.

Model information sources

Release date ↗

10.1±1.8comparison 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 2B (pre-trained), out of 877 with a score, then more from Google.

#modelscorewhereRAMreleased
857BLOOM 1.7B BigScience11±1local~3.1GB2022-07
858Zyte-1B venkycs (aihub-app)10±3local~2.2GB2024-01
859LaMDA 2B (pre-trained) Google10±2never released2022-01
860StableLM-Base-Alpha 7B Stability AI8±1local~35GB2023-04
861Pythia 410M EleutherAI8±2local~1.8GB2023-02
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▁▃▃▆█▇▅▇▃▁▁▁ #510 of 523 * · 5.4% of its score · 1 test

Beats Flan-T5 Large, OPT-66B, Flan-T5 Base here, though they rank higher overall. Trails GPT-Neo 125M, OPT-125M, GPT-2 XL (1.5B) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab1.9% ✎█·▅▃▃▃·▃·▃▃▅ beats 4/12easy · avg 67%▇▇ 5.4%sharp · too hard for it
other tests8 not in a task · 93% of its score
testresultvs the others in its rundifficultycountswhy
MAWPS (CoT-paper union) lab3.1% ✎▅▃█···▅·▃▃▃▅ beats 3/12very easy · avg 94%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%sharp · too hard for it
ASDiv lab3.8% ✎▅▃▃▅··▃▃·▃▃█ beats 4/12easy · avg 83%▇▇▇▇▇▇▇▇ 21%sharp · too hard for it
SVAMP lab2.4% ✎▃▅█···▅·▃▃▃▅ beats 3/12easy · avg 82%▇▇▇▇▇▇▇ 16%sharp · too hard for it
BIG-bench Date Understanding lab8.0% ✎▃·▅·▅▃▅·▃▃·█ beats 3/12medium · avg 52%▇▇▇ 8.5%too hard for it
CommonsenseQA lab20.2% ✎█······▁·▁▁▃ beats 1/12easy · avg 87%▇▇ 3.9%sharp · too hard for it
StrategyQA lab52.6% ✎█·····▅▃▃▅▃█ beats 3/12medium · avg 70%▇ 3.1%too hard for it
BIG-bench Sports Understanding lab49.3% ✎█·····▃·▁·▄▁ beats 1/12medium · avg 81%▇ 3.0%sharp · too hard for it
AQuA-RAT lab17.7% ✎█▁·▁▁·····▂▁ beats 2/12medium · avg 48%▇ 0.5%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… 99%

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= 10.1

$ 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