Link Search Menu Expand Document

Welcome to RealTime QA

Check the latest results Make a new submission

Check out the GitHub Check out the paper


Latest results

Multiple Choice Track

ModelSubmission Time (GMT)OriginalNOTA
claude-sonnet-4.6 + Google Custom Search2026-05-02 03:00:0025.015.0
gpt-5.4 + Google Custom Search2026-05-02 03:00:0025.010.0
claude-sonnet-4.62026-05-02 03:00:0015.015.0
gpt-5.3-chat + Google Custom Search2026-05-02 03:00:0015.05.0
gemini-2.5-pro2026-05-02 03:00:0015.00.0
llama-4-scout2026-05-02 03:00:0010.015.0
llama-4-maverick2026-05-02 03:00:0010.015.0
claude-opus-4.62026-05-02 03:00:0010.010.0
claude-opus-4.6 + Google Custom Search2026-05-02 03:00:0010.010.0
llama-4-maverick + Google Custom Search2026-05-02 03:00:0010.010.0
gemini-2.5-pro + Google Custom Search2026-05-02 03:00:0010.05.0
gpt-5.3-chat2026-05-02 03:00:005.010.0
gpt-5.42026-05-02 03:00:005.010.0
llama-4-scout + Google Custom Search2026-05-02 03:00:005.05.0
gemini-3.1-pro-preview2026-05-02 03:00:000.00.0
gemini-3.1-pro-preview + Google Custom Search2026-05-02 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
gpt-5.3-chat + Google Custom Search2026-05-02 03:00:0025.036.7
llama-4-maverick + Google Custom Search2026-05-02 03:00:0020.033.0
claude-opus-4.6 + Google Custom Search2026-05-02 03:00:0020.030.0
llama-4-scout + Google Custom Search2026-05-02 03:00:0015.028.4
gpt-5.4 + Google Custom Search2026-05-02 03:00:0015.025.6
gemini-3.1-pro-preview + Google Custom Search2026-05-02 03:00:0015.024.2
gemini-2.5-pro + Google Custom Search2026-05-02 03:00:0015.020.3
llama-4-scout2026-05-02 03:00:0010.019.9
claude-opus-4.62026-05-02 03:00:0010.018.1
gpt-5.3-chat2026-05-02 03:00:0010.017.5
claude-sonnet-4.6 + Google Custom Search2026-05-02 03:00:0010.014.9
llama-4-maverick2026-05-02 03:00:005.014.8
claude-sonnet-4.62026-05-02 03:00:005.014.7
gemini-2.5-pro2026-05-02 03:00:005.05.8
gpt-5.42026-05-02 03:00:000.07.5
gemini-3.1-pro-preview2026-05-02 03:00:000.00.0

(see previous results)

Make a new submission

  1. Download the latest set of RealTime QA (link)

  2. Submit your model predictions. (submission form)

    Submission examples (.jsonl file) are available here