Models / Meta
Gets 94 of every 100 tool calls right on the public test. Best at choosing the right tool from several, weaker at making several calls at once.
Llama-3.3-70B-Instruct is made by Meta. It takes text in and answers in text, with a context window of 131,072 tokens.
The live price, read from billing as this page loads. You pay only for the tokens you use, from your credits.
Tool calling (public BFCL v4 test)
Overall: 93.5%*. Picks the right tool and fills in the inputs correctly on 94 of every 100 tasks.
One tool 96% · Picking the right tool 96% · Several calls at once 86%
A task counts as right only if the model calls the right tool with the right inputs. 800 tasks. Run on Oct 29, 2026. *Measured by Spanda Works on third-party hosts, not through Tīrtha. Results through Tīrtha may differ.
Works best with shorter prompts for tool calls in our tests.
Handled several calls at once in our tests.
Measured as Llama-3.3-70B-Instruct-Turbo.
See Llama-3.3-70B-Instruct beside every other model on Tīrtha Bench →
Facts here are read from the maker's published card; claims and benchmarks on that card are the maker's own, not measured by Tīrtha.
Weights: Llama 3.3 Community License. Llama 3.3 Community License. Llama 3.3 Acceptable Use Policy.
Built with Llama
Llama 3.3 is licensed under the Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.