whatmodel.sh / GPT-3 curie (API base model)

GPT-3 curie (API base model)

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

GPT-3 curie (API base model) is a closed-weights language model from OpenAI, released June 2020. Licence: proprietary.

Catalogue identity notes

The original OpenAI API base model 'curie' (2020-2023), retired by OpenAI in January 2024. Not the 2023 replacement babbage-002/davinci-002 and not the InstructGPT 'text-' models. OpenAI never officially published its parameter count, so params_b is omitted.

25.9±1.2comparison only: no current run option verifiedfrom 13 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of GPT-3 curie (API base model), out of 828 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
771OPT-13B (13 billion parameters) Meta26±1local~29GB2022-05
772Granite 4.0 350M IBM26±1local~1.7GB2025-10
773GPT-3 curie (API base model) OpenAI26±1comparison only2020-06
774Alpaca 13B Stanford CRFM26±2comparison only2023-03
775Falcon 7B Instruct TII25±2local~5.9GB2023-04
more from OpenAI
1GPT-6 Astra OpenAI87±1api $20.00/M2026-09
3GPT-6.1 Sol OpenAI85±1api $4.00/M2026-09
7GPT-6 Sol OpenAI83±1api $4.00/M2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests9 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
WinoGrande +165.6% ✎▄·▄·▄▄▄··█·▄ beats 6/7easy · avg 89%▇▇▇▇▇▇▇▇ 21%at its level · several runs
HellaSwag +168.5% ✎▄·█·█··▄▄··▄ beats 6/7very easy · avg 92%▇▇▇▇▇▇▇▇ 19%at its level · several runs
ARC Challenge33.4% ✎▄····▄···█▄▄ beats 2/5easy · avg 79%▇▇▇▇▇▇ 16%sharp
TriviaQA19.6% ✎█···█·███··█ beats 3/5easy · avg 72%▇▇▇▇ 10%typical
LAMBADA (OpenAI version), last-word accuracy +169.3% ✎█·▄··█··█··▄ beats 5/7very easy · avg 90%▇▇▇▇ 8.9%blunt · at its level · several runs
OpenBookQA29.0% ✎▅·······█··▃ beats 3/5medium · avg 52%▇▇▇ 6.9%too hard for it
PIQA +177.9% ✎█··▃··▃▃·▃·▃ beats 6/7easy · avg 89%▇▇▇ 6.6%blunt · at its level · several runs
ARC Easy68.2% ✎▄···▄··█·▄·▄ beats 3/5very easy · avg 90%▇▇ 5.8%at its level
1 more test
testresultvs the others in its rundifficultycountswhy
SciQ91.8% ✎██····███··█ beats 3/5very easy · avg 98%▇▇ 4.6%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · GPT-NeoX-20B: An Open-Source… 71%, EleutherAI GPT-J-6B model car… 29%

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
GPT-NeoX-20B: An Open-Source Autoregressive Language Model — authors' own runs9▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 71%CC BY 4.0
EleutherAI GPT-J-6B model card — EleutherAI lm-evaluation-harness runs4▇▇▇▇▇▇▇▇▇ 29%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 25.9

$ 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