Codesota · Agentic AI · Time Horizon · METR Time HorizonTasks/Agentic AI/Time Horizon
Time Horizon · benchmark dataset · 2024

METR Autonomy Evaluation: 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 Submit a result
§ 01 · Leaderboard

Best published scores.

5 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.


Primary
task-horizon-minutes · higher is better
task-horizon-minutes· primary
5 rows
#ModelOrgSubmittedPaper / codetask-horizon-minutes
01Claude Opus 4APIAnthropicApr 2025METR: Measuring Autonomy in AI Systems (2025 Update)60
02o3APIOpenAIApr 2025METR: Measuring Autonomy in AI Systems (2025 Update)30
03Claude 3.7 SonnetAPIAnthropicApr 2025METR: Measuring Autonomy in AI Systems (2025 Update)14
04o1APIOpenAIApr 2025METR: Measuring Autonomy in AI Systems (2025 Update)4.00
05GPT-4 Turbo (2024)OpenAIApr 2025METR: Measuring Autonomy in AI Systems (2025 Update)2.00
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

1 steps
of state of the art.

Each row below marks a model that broke the previous record on task-horizon-minutes. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · task-horizon-minutes
  1. Apr 1, 2025Claude Opus 4Anthropic60
Fig 3 · SOTA-setting models only. 1 entries span Apr 2025 Apr 2025.
§ 04 · Literature

1 paper
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies
METR Time Horizon — Time Horizon benchmark · Codesota | CodeSOTA