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
llama-4-scout2026-04-18 03:00:0025.015.0
llama-4-maverick2026-04-18 03:00:0020.030.0
claude-sonnet-4.62026-04-18 03:00:0020.015.0
llama-4-maverick + Google Custom Search2026-04-18 03:00:0020.010.0
gpt-5.3-chat2026-04-18 03:00:0015.020.0
claude-opus-4.62026-04-18 03:00:0015.015.0
llama-4-scout + Google Custom Search2026-04-18 03:00:0015.015.0
claude-sonnet-4.6 + Google Custom Search2026-04-18 03:00:0015.010.0
gemini-2.5-pro2026-04-18 03:00:0015.05.0
gpt-5.42026-04-18 03:00:0010.020.0
claude-opus-4.6 + Google Custom Search2026-04-18 03:00:0010.015.0
gpt-5.4 + Google Custom Search2026-04-18 03:00:005.05.0
gemini-3.1-pro-preview2026-04-18 03:00:005.05.0
gemini-2.5-pro + Google Custom Search2026-04-18 03:00:005.00.0
gemini-3.1-pro-preview + Google Custom Search2026-04-18 03:00:005.00.0
gpt-5.3-chat + Google Custom Search2026-04-18 03:00:000.010.0

Generation Track

ModelSubmission Time (GMT)EMF1
llama-4-maverick + Google Custom Search2026-04-18 03:00:0040.050.6
llama-4-scout + Google Custom Search2026-04-18 03:00:0035.045.6
gemini-3.1-pro-preview + Google Custom Search2026-04-18 03:00:0030.039.0
claude-opus-4.6 + Google Custom Search2026-04-18 03:00:0025.041.0
claude-sonnet-4.6 + Google Custom Search2026-04-18 03:00:0025.039.8
gpt-5.3-chat + Google Custom Search2026-04-18 03:00:0020.036.5
claude-opus-4.62026-04-18 03:00:0020.028.8
llama-4-maverick2026-04-18 03:00:0020.026.2
claude-sonnet-4.62026-04-18 03:00:0020.023.3
gpt-5.4 + Google Custom Search2026-04-18 03:00:0015.032.9
gemini-2.5-pro + Google Custom Search2026-04-18 03:00:0015.028.0
gpt-5.3-chat2026-04-18 03:00:0015.022.8
gpt-5.42026-04-18 03:00:0015.020.2
gemini-3.1-pro-preview2026-04-18 03:00:0015.019.8
llama-4-scout2026-04-18 03:00:005.08.9
gemini-2.5-pro2026-04-18 03:00:000.03.5

(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