BenchAtlas

Rankings / Anthropic

Claude Sonnet 4.5

release date unknown

BenchAtlas Index

as of 2026-07-14
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

0 results
No bare-model results yet.

Agent + model results

systems, not bare-model scores
agent + model Sonar Foundation Agent + Claude Sonnet 4.5SWE-bench Verified74.8 %unverifiedSWE-bench Leaderboard
agent + model ante + Claude Sonnet 4.5Terminal-Bench 1.060.3 %unverifiedTerminal-Bench Leaderboard
agent + model Droid + Claude Sonnet 4.5Terminal-Bench 1.057.5 %unverifiedTerminal-Bench Leaderboard
agent + model chaterm + Claude Sonnet 4.5Terminal-Bench 1.052.5 %unverifiedTerminal-Bench Leaderboard
agent + model terminus-2 + Claude Sonnet 4.5Terminal-Bench 1.051.0 %communityTerminal-Bench Leaderboard
agent + model deepagent-desktop + Claude Sonnet 4.5Terminal-Bench 1.050.5 %unverifiedTerminal-Bench Leaderboard
agent + model TerminalBenchAgent + Claude Sonnet 4.5Terminal-Bench 2.046.5 %unverifiedTerminal-Bench Leaderboard
agent + model goose + Claude Sonnet 4.5Terminal-Bench 2.043.1 %unverifiedTerminal-Bench Leaderboard
agent + model alpha + Claude Sonnet 4.5Terminal-Bench 1.038.3 %unverifiedTerminal-Bench Leaderboard

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.

Related variants

Claude Sonnet 4 20250514Claude Sonnet 4.5 20250929Claude Sonnet 4.6Claude Sonnet 4Claude Sonnet 5