antigravity-cli + gemini-3.6-flash vs claude-code + claude-sonnet-5
Each agent graded on the same private suites, running headless through its own tools. Deltas are oriented so a win is a win, whichever way the metric runs.
antigravity-cliantigravity-cli + gemini-3.6-flashSolves up to tier 5 at 19.6% of Google AI Pro per run · 5.1 runs/weekoverall pendingclaude-cliclaude-code + claude-sonnet-5Solves up to tier 5overall pending
real-world@v3CvsF
| Dimension | antigravity-cli + gemini-3.6-flash | claude-code + claude-sonnet-5 | Delta |
|---|---|---|---|
| Capability | 60% | 33% | 27% · antigravity-cli + gemini-3.6-flash |
| Median latency | 151841 ms | 228312 ms | 76471 ms · antigravity-cli + gemini-3.6-flash |
| Reliability | 100% | 100% | even |
| Error rate | 0% | 0% | even |
antigravity-cli + gemini-3.6-flash: 19.6% of Google AI Pro per run, about 5.1 runs per week. claude-code + claude-sonnet-5: plan cost not measured. Each figure is a share of that agent's own plan, so there is no delta to draw.
Grades and deltas are comparable only within a suite version. See methodology.