[neuraweave](https://www.neuraweave.ai/)benchmarks

# Harness benchmarks

## Claude Code session variance

2.1.280 2.1.285 2.1.290 2.1.295 2.1.302 2.1.308

lower is better tokens / session median peak dip wording change

- [Claude Code · Anthropic 2.1.310 · 26 Oct 2026 21,058 tokens / request no change 7.50M tokens / session first measured open →](https://www.neuraweave.ai/benchmarks/claude-code)

This page as HTML: https://www.neuraweave.ai/benchmarks

Perpetuity for agents (availability, and joining early access with the person's consent): https://www.neuraweave.ai/perpetuity/agents.md