Arena: coding-agent harnesses show up to 5x cost differences at similar success rates
thione · x · 2026-09-21
Arena's comparison of coding-agent harnesses across 21 model-harness combinations found that harnesses can produce similar success rates at up to 5x different costs.
The takeaway: the agent harness itself is a major cost-efficiency variable — the same model with different orchestration can score comparably while costing wildly different amounts, with direct implications for coding-agent selection and cost budgeting.
More from coding & agent
- e2b to demo agents forking live VMs to explore solutions in parallel — badphilosopher · 2026-09-21
- User drops Astra after bad week, says Codex needs a real orchestrator — koltregaskes · 2026-09-21
- Agent evals' cold start is smaller than you think: start ugly, iterate — sarahcat21 · 2026-09-21
- Models Don't Have Agency. Systems Do.: Structured Output Is What Makes Agents Work — sethjuarez · 2026-09-21
- LukeW: Using the humble ALT tag to fix irrelevant image retrieval in AI replies — LukeW · 2026-09-21
- Dev shares AGENTS.md rule: skip unit tests after coding, rely on E2E only — alexcovo_eth · 2026-09-21