Head to head / curated pair / cycle 04
Antigravity vs Jules
Both products were given the identical 9 prompt vibeOps specification, 5 times each. Nothing on this page is an impression, all of it is a measurement from the same harness.
Plans across several files at once and reports what it intends to do before doing it, which makes a failed run cheap to diagnose. It is the best value entry in the agent group at present because the licence costs nothing, and that will change. Prompt 6 was the weak point: durable work was queued correctly in three of five runs and left as a timer in the other two.
An asynchronous agent: you hand it a task against a repository and come back to a proposed change. Judged on wall clock that is expensive, and it posts one of the slower medians in the index, but the comparison is not quite like for like since nobody sits and watches it. Change quality was good and the tests it added were real tests rather than assertions that always pass.
Index gap
3.22
Antigravity leads
Axes won
8 / 1
Antigravity versus Jules, of ten axes
Faster median
Antigravity
78.7 s per prompt
Higher pass rate
Jules
75.6%
Every measurement, side by side
Cyan marks the better figure on each row. The delta column is the first product minus the second.
| Measurement | Antigravity | Jules | Delta |
|---|---|---|---|
| Composite index | 71.91 | 68.69 | +3.22 |
| Agent performance (weight 18) | 83.0 | 80.0 | +3.00 |
| Reliability (weight 18) | 73.3 | 75.6 | -2.30 |
| Scalability (weight 13) | 76.0 | 74.0 | +2.00 |
| SEO and GEO (weight 12) | 58.0 | 55.0 | +3.00 |
| API and MCP (weight 9) | 70.0 | 66.0 | +4.00 |
| Integrations (weight 8) | 72.0 | 70.0 | +2.00 |
| Design output (weight 7) | 70.0 | 62.0 | +8.00 |
| Speed (weight 7) | 39.9 | 21.4 | +18.50 |
| Value (weight 5) | 86.0 | 84.0 | +2.00 |
| Code ownership (weight 3) | 96.0 | 96.0 | +0.00 |
| Median seconds per prompt | 78.7 | 146.5 | -67.80 |
| p10 seconds | 45.0 | 84.4 | -39.40 |
| p90 seconds | 123.1 | 292.7 | -169.60 |
| Executions failed | 5 | 4 | +1.00 |
| HTML bytes, no JS | 22.0 KB | 21.0 KB | +1024.00 |
| LCP milliseconds | 1,820 | 1,860 | -40.00 |
| CLS | 0.040 | 0.040 | +0.00 |
| Entry price EUR | 0.00 | 0.00 | +0.00 |
Screenshot diff
Both landing pages, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Antigravity, captured 14 Aug 2026.
Jules, captured 14 Aug 2026.
Speed spread on a shared scale
Antigravity
45.0 / 78.7 / 123.1 seconds
Jules
84.4 / 146.5 / 292.7 seconds
Axis by axis, who wins
Antigravity wins 8 of 10
- Agent performance83.0
- Scalability76.0
- SEO and GEO58.0
- API and MCP70.0
- Integrations72.0
- Design output70.0
- Speed39.9
- Value86.0
Jules wins 1 of 10
- Reliability75.6
Verdict
Antigravity takes the composite by 3.22 points. It wins on the weighted total, but the axis table is where the real decision sits: Antigravity takes 8 axes and Jules takes 1.
If the work in front of you is mostly interface, weight the design and speed rows. If it is a product with an API, webhooks and background jobs, weight agent performance, reliability and the API and MCP row, which together carry 45 of the 100 index points. If the project has to outlive its vendor, read the code ownership row first and treat everything else as secondary.
Both products in this comparison were measured in the same cycle, on the same specification, by the same harness. The per run data for each is on its product page and in /api/runs.json.