Same model, 9.2x token spread: harness matters more than the model
zainhas · x · 2026-09-08
Real-world testing shows the agent harness can impact token usage and end-to-end time more than the model itself. Running GLM 5.3 Flash Max across three frameworks: Codex used 475K tokens in 9 mins, OMP 1.74M in 30 mins, and Opencode 4.36M in 20 mins — a 9.2x token spread on one model. Takeaway: choosing the right harness matters as much as choosing the model for cost and efficiency.
Related event: Coding Harness Matters More Than Model: Token Use Varies 9.2x(2 posts)→
More from coding & agent
- Stanford's PaperFormalizer turns research papers into Lean-verified versions with author in the loop — StanfordUniversity · 2026-10-27
- Hugging Face TRL makes score centering + masked importance sampling default in async GRPO — _lewtun · 2026-10-27
- AutoResearch agent's weird training curve gets dug into instead of discarded — ZimingLiu11 · 2026-10-27
- Firecrawl offers 2.5x credits to a16z Speedrun founders, unveils $75M Series B — devdigest · 2026-10-27
- Chums: open-source Apple Watch app puts Claude Code and Codex on your wrist — brandon_galang · 2026-10-27
- Open-source Clairic Studio turns pasted text into typed data and working code in 5 languages — dfinke · 2026-10-27