Model results

METR Time Horizons

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use as a historical reference for task difficulty measured in human completion time.

Historical time horizon at 50% success, primarily software/ML/security tasks. Imported groups below may use different protocols; this review does not certify each run. Not actively updated after September 8, 2026. Results above 16 human-hours are unreliable for this suite.

Publisher results

← All evaluation groups

METR Time Horizons

Source: METR via Epoch AI
Version: Not reported
Measurement date: Not reported
Metric: min · Higher is better
Evaluation scope: effort 16K · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Claude Opus 4.5
anthropic/claude-opus-4-5
288.9 min
View modelEvidence aggregated
Claude Sonnet 4.5
anthropic/claude-sonnet-4-5
121.95 min
View modelEvidence aggregated
Claude Opus 4.1
anthropic/claude-opus-4-1
113.69 min
View modelEvidence aggregated
Claude Opus 4
anthropic/claude-opus-4
85.56 min
View modelEvidence aggregated
Claude Sonnet 4
anthropic/claude-sonnet-4
74.94 min
View modelEvidence aggregated