Claude Opus 5
First on Android Bench 1.0 at 91.8%. Its best WebDev row is seventh. Opus 5.5, not this model, leads the long-horizon board.
Anthropic · Proprietary · Context 1M · $5 / $25 per million tokens · Fetched 2026-10-10
Benchmark scores
Boards older than 90 days are not counted as recommendationsBenchmarkSettingScoreRankCostAs of
Use it or not
Why
- First on standard Android tasks, the steadier pick for everyday features and migrations.
When not
- The top four sit between 90.2% and 91.8% with overlapping intervals. Long-horizon work belongs to Opus 5.5.