Codesota · Benchmark · METR Time HorizonHome/Leaderboards/METR Time Horizon
Unknown

METR Time Horizon.

Measures the length of tasks AI agents can reliably complete autonomously. Task horizon is the 50th-percentile task length at 50% success. Higher = agent can handle longer multi-step tasks without human intervention.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Task Horizon Minutes

Task Horizon Minutes is the reported evaluation metric for METR Time Horizon. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Task Horizon Minutesverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01Claude Opus 4
Claude Opus 4 (2025). ~1 hour task horizon. Estimated from METR trajectory and Anthropic model card.
verified602025Paper ↗Looks wrong?
02o3
OpenAI o3 (Apr 2025). ~30 min task horizon. METR autonomy evaluation.
verified302025Paper ↗Looks wrong?
03Claude 3.7 Sonnet
Claude 3.7 Sonnet (Feb 2025). ~14 min task horizon. METR autonomy evaluation.
verified142025Paper ↗Looks wrong?
04o1
OpenAI o1 (Sep 2024). ~4 min task horizon. METR autonomy evaluation.
verified4.002025Paper ↗Looks wrong?
05GPT-4 Turbo (2024)
GPT-4 Turbo (Apr 2024). ~2 min task horizon. METR autonomy eval, metr.org/research/autonomy-evals/
verified2.002025Paper ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards