Anthropic

Claude 3 Opus

Announced Mar 4, 2024

Stronger analysis with visual inputs

What could it do?

Anthropic's most capable model at launch, aimed at complex tasks such as research, coding, and financial analysis.

What changed?

Added vision across the Claude 3 family and stronger task performance.

WHY IT MATTERED

Visual analysis

Expanded Claude’s role in complex analysis workflows.

Where it fell short

Can misread visuals and generate unsupported claims.

Research draft

Capabilities describe the developer’s announcement. This entry has not completed source review.

Read original source

Benchmark results

EPOCH AI CAPABILITY ESTIMATE

126.9index points

Tested variant: Claude 3 OpusSource interval: 121.5 to 130.0Variant date in source: Feb 29, 2024

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

1322rating points

Tested: claude-3-opus-20240229Text Arena Overall · October 8, 2026Reported interval: 1319 to 1325194,909 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

Understand the benchmarks Find this release on the chart