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 Search2026-04-25 03:00:0020.010.0
llama-4-scout2026-04-25 03:00:0020.010.0
gpt-5.42026-04-25 03:00:0010.030.0
gpt-5.3-chat + Google Custom Search2026-04-25 03:00:0010.020.0
gpt-5.3-chat2026-04-25 03:00:0010.010.0
gemini-2.5-pro2026-04-25 03:00:0010.010.0
claude-sonnet-4.62026-04-25 03:00:0010.010.0
claude-opus-4.62026-04-25 03:00:0010.010.0
claude-opus-4.6 + Google Custom Search2026-04-25 03:00:0010.010.0
gemini-2.5-pro + Google Custom Search2026-04-25 03:00:0010.00.0
gpt-5.4 + Google Custom Search2026-04-25 03:00:000.020.0
llama-4-maverick2026-04-25 03:00:000.010.0
gemini-3.1-pro-preview2026-04-25 03:00:000.00.0
gemini-3.1-pro-preview + Google Custom Search2026-04-25 03:00:000.00.0
llama-4-scout + Google Custom Search2026-04-25 03:00:000.00.0
llama-4-maverick + Google Custom Search2026-04-25 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
llama-4-maverick + Google Custom Search2026-04-25 03:00:0040.045.0
gpt-5.3-chat + Google Custom Search2026-04-25 03:00:0040.044.0
gemini-3.1-pro-preview2026-04-25 03:00:0040.040.0
llama-4-maverick2026-04-25 03:00:0040.040.0
claude-opus-4.6 + Google Custom Search2026-04-25 03:00:0030.038.2
claude-opus-4.62026-04-25 03:00:0030.035.9
gpt-5.4 + Google Custom Search2026-04-25 03:00:0030.035.0
gemini-3.1-pro-preview + Google Custom Search2026-04-25 03:00:0030.035.0
claude-sonnet-4.62026-04-25 03:00:0030.035.0
llama-4-scout2026-04-25 03:00:0030.035.0
claude-sonnet-4.6 + Google Custom Search2026-04-25 03:00:0020.027.0
gpt-5.3-chat2026-04-25 03:00:0020.025.0
llama-4-scout + Google Custom Search2026-04-25 03:00:0020.025.0
gpt-5.42026-04-25 03:00:0020.020.0
gemini-2.5-pro + Google Custom Search2026-04-25 03:00:0010.013.3
gemini-2.5-pro2026-04-25 03:00:0010.010.0

(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