SECOND RUN/ COMPUTE

An open record of computational work

Find a tested way
to run your work.

Compare configurations, methods and costs. Check the claim, keep the result, and give the next person a better starting point.

Execution paths

Results keep their original workload and cost basis. Unknown fields stay unmeasured.

SelectExecution pathWorkload / methodAcceptedCost / acceptedFirst token
median / p99
EvidenceInspect
What belongs in this board?

Model APIs, local models, hardware configurations and assisted workflows can all appear. Each result retains its task, acceptance rule and source. Ranks group results by their task and acceptance criteria. Repeated requests remain separate from independent repetitions. Availability, uptime, energy and autonomy require their own observations.

Current seed records come from Second Run campaigns and source-linked TierBench history. Historical summaries are not upgraded into new hardware measurements. Prices are dated observations, not live quotes.

Result