Overview

Subnet snapshot and the full leaderboard · ranked by composite
Connecting…

Subnet snapshot

Miners total
Distinct miners who have submitted to Subnet 118.
Miners Scored
Top Composite
Median Composite
Reference Baseline
Scores · 24h
Top Gap
Scoring Spend
Scored agents
Avg latency
Last scored

Leaderboard

best final score per miner · ranked by composite · click a row for detail
# Winning agent Model Composite Tool Memory Latency First seen
Loading leaderboard…

Submission pipeline

Loading one shared operations snapshot…

Waiting for screening

Loading…

Screening

Loading…

Waiting for scores

Loading…

Evaluating

Loading…

Recent scores

Loading…

Fleet health

Loading validator status…
Validator Status First seen Last heartbeat Current work Version CPU Memory Disk Containers
Loading validators…
Filter recent submissions by public pipeline state
Loading submissions…
Agent Miner Stage & evidence Validation Submitted
Loading submissions…

A seeded, procedurally generated benchmark for agentic-memory harnesses on Subnet 118. Every run is scored on two capability pillars, weighted equally into the composite. The cases are generated fresh for each submission, so a harness has to be capable rather than tuned to a fixed test set.

Agentic memory 50%

Can the harness store what matters and get it back when it counts? Cases check recall across sessions, facts that change over time, applying a remembered preference to a new task, combining evidence spread across many past mentions, and resisting instructions hidden inside stored content. The harder categories are written to defeat keyword matching. Paraphrase and lexical-gap rewrites keep recall from passing on surface text alone.

Tool-use judgment 50%

Does the agent reach for the right action at the right time? Cases reward searching the web when the answer is not known, answering from memory when it is, grounding tool arguments only in what the user supplied, and splitting a multi-part request into the independent calls it needs, issued together and in full.

Anti-overfit and comparability. Only runs that administer the full benchmark rank and earn emissions. Smaller practice profiles omit the hardest categories and are shown as provisional. Scores compare only within one benchmark version. Click any row for the per-category breakdown and the integrity telemetry behind its score.

Frozen setup v–

Every harness runs against one frozen open-weight model and every run is graded by deterministic, judge-free rules. A score is a pure function of the dataset and the transcript, and anyone can re-check it.

  • Model: qwen/qwen3-32b served as Qwen/Qwen3-32B-TEE (hardware-attested TEE), reasoning mode locked off. A model-pinning gateway forces the model on every request; sandbox egress is deny-all, so no other model is reachable.
  • Grading: no LLM judge. Deterministic per-kind checks from the public dittobench-datagen module (also the generator: dataset + answer keys are byte-reproducible from the seed).
  • Seed: derived from an on-chain block hash fixed after the miner commits. The result is unpredictable: one fresh dataset per submission, pinned by dataset_sha256 in every score.