Compare AI models

Specifications
Parameters
—9B
Context window
200k128k
Benchmarks
HumanEval
88.1%82.3%
Overview
CompanyAnthropicZ.ai
Release dateOct 22 2024Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX4-ALL-9B shipped 109 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 128k (CodeGeeX4-ALL-9B). Claude 3.5 Haiku is closed, while CodeGeeX4-ALL-9B is open weight.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs CodeGeeX4-ALL-9B at 82.3%.