GPT-4

GPT model for general reasoning, writing, coding, and tool-assisted tasks

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

From the lab

Related article · Mar 14, 2023GPT-4
RELEASE DATENov 6, 2023
WEIGHTSClosed weights
CONTEXT WINDOW8.2K
MAX OUTPUT8.2K
REASONINGNo
TOOL CALLINGYes
INPUTStext
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.