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-opus-4.62026-08-01 03:00:0020.020.0
llama-4-scout2026-08-01 03:00:0020.015.0
llama-4-maverick2026-08-01 03:00:0015.015.0
claude-opus-4.6 + Google Custom Search2026-08-01 03:00:0015.05.0
gpt-5.3-chat2026-08-01 03:00:0010.020.0
gpt-5.42026-08-01 03:00:0010.015.0
claude-sonnet-4.62026-08-01 03:00:0010.010.0
gemini-3.1-pro-preview2026-08-01 03:00:0010.00.0
llama-4-maverick + Google Custom Search2026-08-01 03:00:0010.00.0
gpt-5.3-chat + Google Custom Search2026-08-01 03:00:005.015.0
gpt-5.4 + Google Custom Search2026-08-01 03:00:005.00.0
gemini-2.5-pro + Google Custom Search2026-08-01 03:00:005.00.0
gemini-3.1-pro-preview + Google Custom Search2026-08-01 03:00:005.00.0
claude-sonnet-4.6 + Google Custom Search2026-08-01 03:00:005.00.0
gemini-2.5-pro2026-08-01 03:00:000.010.0
llama-4-scout + Google Custom Search2026-08-01 03:00:000.010.0

Generation Track

ModelSubmission Time (GMT)EMF1
claude-opus-4.6 + Google Custom Search2026-08-01 03:00:0030.040.8
llama-4-scout + Google Custom Search2026-08-01 03:00:0030.040.5
gpt-5.4 + Google Custom Search2026-08-01 03:00:0025.038.6
llama-4-maverick + Google Custom Search2026-08-01 03:00:0025.037.6
claude-sonnet-4.62026-08-01 03:00:0025.028.6
gpt-5.3-chat + Google Custom Search2026-08-01 03:00:0020.036.0
llama-4-scout2026-08-01 03:00:0020.028.9
claude-opus-4.62026-08-01 03:00:0020.027.6
gemini-3.1-pro-preview + Google Custom Search2026-08-01 03:00:0020.025.6
gemini-3.1-pro-preview2026-08-01 03:00:0020.022.3
gpt-5.3-chat2026-08-01 03:00:0015.025.1
claude-sonnet-4.6 + Google Custom Search2026-08-01 03:00:0015.021.9
gpt-5.42026-08-01 03:00:0010.021.0
llama-4-maverick2026-08-01 03:00:0010.019.2
gemini-2.5-pro2026-08-01 03:00:0010.016.9
gemini-2.5-pro + Google Custom Search2026-08-01 03:00:0010.016.0

(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