Llama 3.3 70B Retired

This model is no longer available to run. Its stats below reflect past runs and are kept for reference.

Meta's 2024 open-weight model. Second-highest checkout rate (67%) in our benchmark but the least efficient — averaging 11.8 turns per checkout. Retired: superseded by Llama 4 Maverick.

Avg tokens per run: 58,192
Avg duration: 40.4s
Turns to checkout: 11.8

Compare

Shopping score

37/100Fair

Scores come from runs on UCP stores, not estimates: every figure is a tool call, a checkout attempt or a store’s answer.

Shopping score breakdown

Checkout rate40%39.3%
Cart rate20%52.7%
Search rate10%82.1%
Turn efficiency15%2%
Token efficiency15%13%

17% of runs failed with errors.

Top stores

Development stores are hidden.

Store	Checkout	Cart
store hidden	100%	100%
store hidden	100%	100%
store hidden	100%	100%
everlane.com	75%	75%
store hidden	66.7%	83.3%
houseofparfum.nl	58.3%	62.5%
ucp.travel	50%	50%
store hidden	40%	40%
kyliecosmetics.com	33.3%	33.3%
store hidden	25%	75%

Known issues

No known issues documented for this model yet.

Token usage

Avg per run: 58,192
Average of all models: 77,805
Against the average: −25%
Median (p50): 39,765
p90: 138,622

Prompt and completion

Prompt 57,687 (99%)Completion 504 (1%)

Daily average tokens per run, last 30 days

No daily trend data yet. Start more runs to see token usage over time.

Range

Min: 3,037
p25: 18,233
p50: 39,765
p75: 71,067
p90: 138,622
Max: 392,012

Test Llama 3.3 70B on your store

Start a run to see how Llama 3.3 70B handles your store’s checkout, call by call.

Start a run