Anthropic

Claude Opus 4.6

Announced Feb 5, 2026

More reliable complex work

What could it do?

Anthropic announced gains in coding, agents and enterprise workflows.

What changed?

A new Opus generation after 4.5.

WHY IT MATTERED

Focused on reliability and precision.

Where it fell short

Developer claims; no independent test by this site.

Sources checked Oct 7, 2026

Release facts were checked against the sources below. Performance claims belong to the developers; we have not independently tested these models.

Developer announcement or release log

Benchmark results

EPOCH AI CAPABILITY ESTIMATE

155.2index points

Tested variant: Claude Opus 4.6Source interval: 153.4 to 157.3Variant date in source: Feb 5, 2026

A benchmark estimate, not a percentage or capability multiplier. Reasoning settings are not specified in this source table. Historical estimates can change in later snapshots.

Epoch AI methodology ↗Download the source snapshotChecked Oct 7, 2026 · CC BY 4.0

PUBLISHED BENCHMARK RESULT

1504rating points

Tested: claude-opus-4-6-highText Arena Overall · October 8, 2026Reported interval: 1501 to 150779,415 votes

One explicitly named variant per release. Scores come from the same Overall snapshot; preliminary entries and reported intervals are preserved. These are current ratings of earlier variants, not their launch day ratings.

Source: Text Arena ↗Download selected resultsChecked Oct 8, 2026

PUBLISHED BENCHMARK RESULT

75.6%% resolved

Tested: Claude 4.6 Opus500 tasks · mini-SWE-agent v2.0.0Run: Feb 17, 2026 · Effort: Not specifiedPublished submission; not marked as checked by the benchmark team

Only mini-SWE-agent v2.0.0 submissions, one run per model. Reasoning effort varies and is labelled. These are published submissions, not a rerun by Leapscope. Latest included release: February 5, 2026; latest run: February 26, 2026.

Source: SWE bench Verified ↗Download selected resultsChecked Oct 8, 2026

Understand the benchmarks Find this release on the chart