Devin review
Ambitious autonomy that does not yet pay off — too little finished for the price to make the shortlist.
Tested score
5.8/10
- Task completion·25%5.5
- Code quality·20%6.0
- Speed·15%5.6
- Value for money·15%5.2
- Learning curve·15%6.5
- Team & security·10%6.4
Weights are fixed for the whole category and published in How we test.
The verdict
Cut this cycle: Devin’s fully-autonomous pitch is appealing, but on our fixed tasks it finished too little for the money — the lowest score on the board and well below the shortlist bar.
Who this is wrong for
- You need a predictable cost-to-output ratio — the autonomy did not finish enough to justify the price.
Devin Team — $500/mo
Commission-earning link. Score was locked on 12 Jul 2026, before terms were checked.
The test log
Same 12 tasks run against every agent in this category
| # | Task | Result | Time | Note |
|---|---|---|---|---|
| 1 | Cross-service migration touching auth and billing | Failed | 31m | Ran autonomously for a long time and delivered too little finished work. |
Showing 1 of 12
Pricing at time of testing
checked 12 Jul 2026Team
$500/mo
Autonomous engineer seats
What we testedTested by aitools.reviews
Tested · 5.8/10
AI coding agents · Jul 2026
Vendors scoring 7.5+ may embed this badge. It carries the score and the date — and it updates when we re-test.