From e3d4f42143b2a4dcc986fc020efac1e884d79bbe Mon Sep 17 00:00:00 2001 From: RapidPoseidon Date: Mon, 6 Jul 2026 14:25:37 +0000 Subject: [PATCH] docs(mri): document leaderboard jobs property Co-Authored-By: lino --- docs/mri.md | 16 ++++++++++++++-- docs/mri_advanced.md | 28 ++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 2 deletions(-) diff --git a/docs/mri.md b/docs/mri.md index cf2dd63c4..739323b31 100644 --- a/docs/mri.md +++ b/docs/mri.md @@ -197,8 +197,20 @@ leaderboard = benchmark.leaderboards[0] # Get the standings standings = leaderboard.get_standings() # Returns a pandas dataframe +``` + +Every model evaluation on a leaderboard is carried out by a **job**. The `jobs` +property exposes those jobs so you can drill into the raw comparison results +behind the standings: -# Access the jobs that ran for this leaderboard +```python +# All jobs that have run for this leaderboard (most recent first) for job in leaderboard.jobs: - results = job.get_results() + print(job.name, job.get_status()) + results = job.get_results() # RapidataResults for that evaluation ``` + +Each entry is a full `RapidataJob`, so the usual methods (`get_results()`, +`get_status()`, `view()`, ...) are available. See +[Model Ranking Insights Advanced](mri_advanced.md#accessing-the-underlying-jobs) +for more. diff --git a/docs/mri_advanced.md b/docs/mri_advanced.md index bab2f8fe3..9fa72d442 100644 --- a/docs/mri_advanced.md +++ b/docs/mri_advanced.md @@ -201,6 +201,34 @@ participant = benchmark.participants[0] participant.delete() ``` +## Accessing the Underlying Jobs + +The standings and win/loss matrix are aggregates. If you need the raw responses +behind them, use the leaderboard's `jobs` property: every model evaluation on a +leaderboard runs as a job, and this returns all of them, most recent first. + +```python +leaderboard = benchmark.leaderboards[0] + +jobs = leaderboard.jobs # list[RapidataJob], newest first +print(f"{len(jobs)} evaluations have run for this leaderboard") +``` + +Each item is a full `RapidataJob`, so you can pull the detailed comparison +results, check status, or open a job in the dashboard: + +```python +for job in leaderboard.jobs: + if job.get_status() != "Completed": + continue + + results = job.get_results() # RapidataResults — the individual matchups + df = results.to_pandas() # or work with the raw dict directly +``` + +Runs that don't yet have an associated job (for example, an evaluation still +being set up) are skipped, so the list only contains jobs you can act on. + ## References - [RapidataBenchmarkManager](/reference/rapidata/rapidata_client/benchmark/rapidata_benchmark_manager/) - [RapidataBenchmark](/reference/rapidata/rapidata_client/benchmark/rapidata_benchmark/)