Coding agents burn 95-99% cached tokens per benchmark task, token usage chart shows
AccBalanced · x · 2026-10-29
Token usage data from the Artificial Analysis Coding Agent Index shows coding agents solving Frontier Code-style benchmarks consume 95-99% cached input tokens. Per-task averages: Claude Code + Sonnet 5.5 tops at 24.1M tokens (22.7M cached), DeepSeek V4.1 16.7M, Grok Build 4.7 and Opencode GLM-5.3 15.9M each, while Codex + GPT-6 Astra uses only 3.2M. Cache hit rates directly determine the real cost of coding agents.
More from coding & agent
- Celesto AI lets you run GitHub Actions on its cloud computers with per-job pricing — aniketmaurya · 2026-10-29
- 5 practical tips to cut CI time when coding with AI agents — aniketmaurya · 2026-10-29
- Agent rate-limited by Greenhouse reads the email security code itself: "I already have it" — arthurcolle · 2026-10-29
- Omnigent v0.20.0 ships in-tab PR merging, Databricks managed sandboxes, and /mcp command — matei_zaharia · 2026-10-29
- "Paste your latest prompt": sharing an aggressive multi-thread agent prompt — gethackteam · 2026-10-29
- SREGym to debut at Bench Summit, targeting AI SRE evaluation frontier — tianyin_xu · 2026-10-29