Claude Code task costs: $2.89 medium to $44.22 max, while Codex max scores similar at $1.51
ArtificialAnlys · x · 2026-11-14
Artificial Analysis published pay-per-token cost-per-task numbers for coding agents:
- Claude Code with Fable 5.2: medium $2.89 (Index 53), high $7.51 (58), xhigh $15.47 (58), max $44.22 (56) — medium, high and xhigh sit on the Pareto line; max burns money for no gain
- Codex with GPT-6.1 Sol (max) scores 52 at just $1.51 per task
- Chart also shows much cheaper options like Muse Code + Muse Max at $0.22 and DeepSeek at $0.32
Takeaway: higher reasoning effort barely moves scores while costs explode; low tiers dominate value.
Related event: Artificial Analysis Coding Agent Index v2.1: Claude Duo Tops Chart(3 posts)→
More from coding & agent
- Google's Antigravity multiagent proves 2013 info-theory conjecture in Lean 4 — ymatias · 2026-11-14
- Read-only MCP setup lets Claude Code audit a Proxmox lab — Worldly_Piglet_7040 · 2026-11-14
- Dev finds asking LLMs for prompt and tool design advice often hurts results — mimi10v3 · 2026-11-14
- Yohei Nakajima to headline 'Agents on the Frontier' Pro Series live deep dive next Tuesday — ColleenMBrady · 2026-11-14
- Yogurt: open-source local-first Granola alternative for private AI meeting notes — supportingthedogs · 2026-11-14
- Anthropic Breaks Down the Five Primitives Behind Always-On AI Agents — dotey · 2026-11-14