FrontierCode 2: Anthropic models burn 2-3x tokens, cost 10-50x more than open rivals
bookwormengr · x · 2026-10-28
Citing 1337hero's analysis of the FrontierCode 2.0 benchmark, bookwormengr notes Anthropic models generate 200-300% more tokens on frontier coding tasks, take twice as long, and cost 10-50x more. Artificial Analysis's Token Usage chart shows Claude Code + Sonnet 5 at a median 18.9M tokens (peaks over 60M), vs 9M for DeepSeek, 8.1M for GLM-5.3, 3.5M for GPT-6.1-Terra and 2.2M for GPT-6 Astra. Takeaway: for frontier tasks go Anthropic; open models retain far better economics and could close the gap with more test-time compute.
Related event: FrontierCode 2.0 leaderboard lands; hidden model Obsidian 3 tops the chart(10 posts)→
More from coding & agent
- Parallel's Decisions API lands on Merge Gateway at $0.001 per request — shensi · 2026-10-29
- Drew Breunig's State of Context Engineering: 6 tactics, one key tradeoff — rseroter · 2026-10-29
- GitHub demos Copilot Code Review Max with stacked PR merge at Universe — kimmonismus · 2026-10-29
- IBM TechXchange: Three Big Challenges of Adopting AI Agents in the Enterprise — craigmullins · 2026-10-29
- Pydantic Author Samuel Colvin on Setting Up Feedback Loops for Code-Writing Models — samuelcolvin · 2026-10-29
- Open-Source Coding Tools Climb T3 Charts: opencode Hits #2 Most Engaged Repo — MeetPatelTech · 2026-10-29