Claude Opus 4.8 Claude Code
Not yet ranked: too few independent results so far.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Agents & tools58
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Coding
| Benchmark | default | Source |
|---|---|---|
| SWE-bench (Vals)not in index | 85.8%#16 | Vals AI |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench 2.1 (Vals) | 69.7%#21 | Vals AI |
See also
Data as of 9 Sept 2026. Compare with another model.