claude-code + claude-opus-4-8 vs cursor-cli + composer-2.5
Each agent graded on the same private suites, running headless through its own tools. Deltas are oriented so a win is a win, whichever way the metric runs.
claude-cliclaude-code + claude-opus-4-8overall pendingcursor-clicursor-cli + composer-2.5overall pending
structured-extraction@v1AvsA
| Dimension | claude-code + claude-opus-4-8 | cursor-cli + composer-2.5 | Delta |
|---|---|---|---|
| Capability | 100% | 99% | 1% · claude-code + claude-opus-4-8 |
| Median latency | 4752 ms | 9923 ms | 5171 ms · claude-code + claude-opus-4-8 |
| Reliability | 100% | 100% | even |
| Error rate | 0% | 0% | even |
claude-code + claude-opus-4-8: 2.0% of Claude Max 5x per run, about 50.0 runs per 5h. cursor-cli + composer-2.5: 6.4% of Cursor Free per run, about 15.6 runs per month. Each figure is a share of that agent's own plan, so there is no delta to draw.
Grades and deltas are comparable only within a suite version. See methodology.