Blog

AI Coding Tools Glossary

Test-time compute (parallel sampling)

Running a model multiple times on the same task and selecting the best attempt, raising benchmark scores at extra cost.

Vendors report two numbers for the same model: single attempt and 'with parallel test-time compute'. Anthropic reports Claude Opus 4 at 72.5% on SWE-bench Verified single-run and 79.4% with parallel sampling and selection. When comparing benchmark claims, check which regime is reported; leaderboards like SWE-bench Pro require a single trajectory.

Source: Introducing Claude 4 — Anthropic

See the numbers behind this term: AI Coding Tools Statistics 2026.