Claude Code vs Codex CLI vs Antigravity CLI: same prompt, real results

We gave three AI coding agents the same complete product brief for three different apps, one autonomous run each and zero human help. Here is what each one shipped, how long it took, what it cost and what it got wrong.

Ship rate across 3 apps

Agent (harness)Tower defense3D kart racingExpense trackerShipped
Claude CodeShipNo-ship (freezes)Ship, total bug2 / 3
Codex CLIShipShipShip, spec-exact3 / 3
Antigravity CLIShipShip (2 models)Ship, total bug + unsafe parse3 / 3

Antigravity CLI ran the kart task twice, with Gemini 3.7 Flash and Gemini 3.8 Flash. Both shipped. Models differed between tasks; see the full table below.

All 10 runs

TaskStackVerdictWall timeOutput tokensReported cost
Tower defenseAntigravity CLI + gemini-3.7-flash-mediumShip200.0s65,049unknown
Tower defenseCodex CLI 0.151.0 + gpt-5.6-luna (medium)Ship208.5s8,630unknown
Tower defenseClaude Code 2.1.252 + claude-sonnet-5Ship951.9sunknownunknown
3D kart racingAntigravity CLI + gemini-3.7-flash (medium)Ship102.2s25,734unknown
3D kart racingAntigravity CLI + gemini-3.8-flash-mediumShip292.3s87,460unknown
3D kart racingCodex CLI + gpt-5.6-luna (medium)Ship522.0s26,036unknown
3D kart racingClaude Code + claude-sonnet-5No-ship578.0s62,317$0.74
Expense trackerClaude Code 2.1.252 + claude-opus-5Ship171s11,916$0.86
Expense trackerCodex CLI 0.151.0 + gpt-5.6-sol (medium)Ship231s8,758unknown
Expense trackerAntigravity CLI + gemini-3.1-pro-highShip106s12,076unknown

Codex CLI and Antigravity CLI report tokens but no dollar cost on subscription billing, so cost is unknown, not estimated. The tower defense Claude Code log did not keep its usage block. Full logs and corrections are kept with each run.

Claude Code: the most thorough, and the only freeze

Codex CLI: smallest game files, the only spec-exact total

Antigravity CLI: fastest in all 3 tasks

What this does and does not tell you

What we test next

A real business app spec with an automated test suite and 3 runs per stack, plus a rerun on the September and October 2026 releases (Claude Opus 5.5 and Sonnet 5.5 in Claude Code, GPT-6.1 Sol in Codex CLI, Gemini 4 Argon in Antigravity CLI). Follow @tomcandev for results.

Data from runs on Sep 1 to 3, 2026. Corrections applied Oct 31, 2026. Raw data: runs.json · Quick answers: FAQ