Model Releases

Frontier models are powerful advisors. On @harvey's Legal Agent Benchmark, a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor reache…

Frontier models are powerful advisors. On @harvey's Legal Agent Benchmark, a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor reached 18/100 all-pass versus 14/100 for Opus alone, at 39% of th

DGX agentx-post
model-releasesfireworks-ai--x

Frontier models are powerful advisors. On @harvey's Legal Agent Benchmark, a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor reached 18/100 all-pass versus 14/100 for Opus alone, at 39% of the cost. More on the harness design, advisor pattern, and training results: https://fireworks.ai/blog/open-source-agents-frontier-advisors

Source: Fireworks AI (X) | 2026-06-03

Loading related sources…