Amp 2026.03.05
Amp 2026.03.05 was released on .
Summary
GPT-5.4, The New Oracle Habemus oraculum! We have a new oracle in Amp and it's GPT-5.4. It's a great model. In our internal evals response quality went from 60.8% (GPT-5.2) to 68.2% (GPT-5.4). Mean...
Release Context
- This was the 15th Amp release of 2026 tracked by Havoptic.
- It shipped 14 days after Amp 2026.02.19 (February 19, 2026).
Shipped around the same time
Within 3 days of this release, other AI coding tools also shipped:
- OpenCode v1.2.21 (March 7, 2026)
- Claude Code v2.1.71 (March 6, 2026)
- GitHub Copilot CLI v1.0.2 (March 6, 2026)
- Cline v3.71.0 (March 6, 2026)
- GitHub Copilot CLI v0.0.423 (March 6, 2026)
Compare Amp
- Amp vs Claude Code
- Amp vs OpenAI Codex CLI
- Amp vs Cursor
- Amp vs Gemini CLI
- Amp vs Kiro CLI
- Amp vs GitHub Copilot CLI
- Amp vs Devin Desktop
- Amp vs Antigravity CLI
- Amp vs Grok Build
- Amp vs Cline
- Amp vs OpenCode
- Amp vs Zed
- Amp vs Factory Droid
- Amp vs Devin
- Amp vs Lovable
- Amp vs GitHub Copilot in VS Code
- Amp vs Replit Agent
- Amp vs Bolt
- Amp vs v0
Release Notes
GPT-5.4, The New Oracle Habemus oraculum! We have a new oracle in Amp and it's GPT-5.4. It's a great model. In our internal evals response quality went from 60.8% (GPT-5.2) to 68.2% (GPT-5.4). Mean latency is down from ~6.7min to ~4.9min. In Amp's smart mode GPT-5.4 works really well with Opus 4.6, which is smart mode's current main model. They complement each other with the oracle bringing sage advice on architecture, code reviews, and tricky bugs to the context window, just as we're used to from previous incantations. On top of that, we also decided to add the oracle subagent to deep mode. Now you might wonder, since deep mode currently uses GPT-5.3-Codex as the main model, why add another GPT model in the same mode? Does that even make sense? We think it does. GPT-5.3-Codex is fantastic at coding (as Codex models tend to be), which is exactly why it is the main model in deep, but the oracle is plain GPT-5.4, a non-Codex model. Less a code specialist, more an all-rounder. That gives us two models from the same family, but trained for different goals, with different system prompts, in the same mode — two distinct voices in the same conversation. We're still learning what GPT-5.4 can do in practice. There are very likely hidden smarts and treasures we haven't found yet. Let us know once you do.
Other Recent Amp Releases
- 2026.10.19 (October 19, 2026)
- 2026.10.16 (October 16, 2026)
- 2026.10.13 (October 13, 2026)
- 2026.10.12 (October 12, 2026)
- 2026.10.12.2 (October 12, 2026)
Upgrading from 2026.03.05? See all 72 releases since.