Best AI for a task

Each page names the model with the highest reported score on a public benchmark that directly tests that task, with the source and its date, then gives you prompts to try it on your own work. We only make a page when a matching benchmark and matching prompts both exist.

Best AI for contract drafting and review

As of Oct 2026, the highest reported score on Legal Benchmarks: Contract Workflows is shared by Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta) at 48.4%, per Legal Benchmarks.

Benchmarks: Legal Benchmarks: Contract Workflows · 2 promptsSee the leaders Best AI for data extraction from documents

As of Oct 2026, the highest reported score on Legal Benchmarks: Data Extraction is Claude Opus 5.5 (Anthropic) at 76.7%, per Legal Benchmarks.

Benchmarks: Legal Benchmarks: Data Extraction · 3 promptsSee the leaders Best AI for financial analysis

As of 19 Oct 2026, the highest reported score on Finance Agent is Claude Opus 5.5 (Anthropic) at 67.85%, per Vals AI.

Benchmarks: Finance Agent, CorpFin v2 · 2 promptsSee the leaders Best AI for fixing code and GitHub issues

As of 1 Sep 2026, the highest reported score on SWE-bench Verified is Claude Opus 5 (Anthropic) at 97.0%, per Vals AI. The source no longer updates this leaderboard.

Benchmarks: SWE-bench Verified, LiveCodeBench · 4 promptsSee the leaders Best AI for AI agents and terminal automation

As of 19 Oct 2026, the highest reported score on Terminal-Bench 4.0 is Claude Opus 5.5 (Anthropic) at 65.15%, per Vals AI.

Benchmarks: Terminal-Bench 4.0, Terminal-Bench 2.1 · 4 promptsSee the leaders

Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results