JobBench

Reported in recent model launches

These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.

What it measures

Meta’s reported professional-tool-use evaluation measures a slice of work performed through tools.

How to read the result

Look for verified task outcomes and required artifacts rather than relying on an assistant’s account of what it completed.

Limits and comparison traps

The reviewed launch identifies the benchmark but does not provide every detail needed for independent replication. Keep this source limitation visible.

Benchmark reference notes

Occupational multi-step workflow benchmark reported in Meta Muse Wonder.

Where this fits in an evaluation suite

A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.