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
Long-document questions test extraction, synthesis, and reasoning across substantial inputs.
How to read the result
Pair this with retrieval stress tests to separate locating an item from integrating several pieces of evidence.
Limits and comparison traps
Advertised context length is not an observed reasoning score. Pin tokenizer, document length, position, and scoring version.
Benchmark reference notes
Evaluates extraction, multi-hop reasoning, and synthesis over 10k–100k token document sets (cl100k_base).
Where this fits in an evaluation suite
A large context window is a capacity specification. Successful retrieval and cross-document reasoning are observed capabilities. Test both at the actual lengths your workflow needs.
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
Use the exact implementation, version, task subset, tool access, attempt budget, and judge described by the 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.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.