Codesota · Natural Language Processing · Question Answering · Natural QuestionsTasks/Natural Language Processing/Question Answering
Question Answering · benchmark dataset · 2019 · EN

Natural Questions: a Benchmark for Question Answering Research.

Open-domain QA benchmark built from real Google search queries with answers annotated from Wikipedia pages.

Paper ↗Download datasetSubmit a result ↵
§ 01 · Leaderboard

Best published scores.

5 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
f1 · higher is better
accuracy
5 rows
#ModelOrgSubmittedPaper / codeaccuracy
01LLaMA-65B—Feb 2023LLaMA: Open and Efficient Foundation Language Models · code39.90
02Llama 2 70B (5-shot)—Jul 2023Llama 2: Open Foundation and Fine-Tuned Chat Models · code33
03OLMo-2-7B-1124 (olmOCR-peS2o)—Feb 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Visio… · code29.10
04Helium—Sep 2024Moshi: a speech-text foundation model for real-time dial… · code23.30
05SmoLM2 (1.7B)—Feb 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of … · code8.70
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 04 · Literature

5 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies