Claude Opus 4.6 vs Claude Opus 5.5
Claude Opus 5.5 reads a 26.2K-token pull request for $0.1048, 20% less than Claude Opus 4.6 ($0.131). Both are Claude Opus models, so the difference is one version of the same line against another.
Side by side
| Figure | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| Price tier | Frontier | Frontier |
| Bugs caughtshare of known bugs | – | 90% |
| False alarmsper clean PR | – | 1.7 |
| Cost per reviewmeasured | – | $0.1525 |
| Cost per bug caught | – | $0.1921 |
| Exact linecatches on the expected lines | – | 89% |
| Review timemean | – | 33s |
| Typical review calllist price | $0.1915 | $0.1532 (better) |
| Input / 1M tokens | $5.00 | $4.00 (better) |
| Output / 1M tokens | $25.00 | $20.00 (better) |
| Context window | 1M | 1M |
Not benchmarked yet
Claude Opus 4.6 isn't benchmarked yet, so this page compares list prices only. Measured bugs caught, false alarms and a bug-by-bug comparison appear here once both have results.
See measured models