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
gpt-5.42026-05-09 03:00:0010.025.0
claude-sonnet-4.62026-05-09 03:00:0010.00.0
llama-4-maverick + Google Custom Search2026-05-09 03:00:0010.00.0
llama-4-maverick2026-05-09 03:00:005.010.0
gpt-5.3-chat2026-05-09 03:00:005.05.0
gpt-5.4 + Google Custom Search2026-05-09 03:00:005.05.0
gemini-2.5-pro2026-05-09 03:00:005.00.0
gemini-2.5-pro + Google Custom Search2026-05-09 03:00:005.00.0
gpt-5.3-chat + Google Custom Search2026-05-09 03:00:000.05.0
gemini-3.1-pro-preview2026-05-09 03:00:000.05.0
claude-sonnet-4.6 + Google Custom Search2026-05-09 03:00:000.05.0
claude-opus-4.62026-05-09 03:00:000.05.0
claude-opus-4.6 + Google Custom Search2026-05-09 03:00:000.05.0
llama-4-scout2026-05-09 03:00:000.05.0
gemini-3.1-pro-preview + Google Custom Search2026-05-09 03:00:000.00.0
llama-4-scout + Google Custom Search2026-05-09 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
gpt-5.3-chat + Google Custom Search2026-05-09 03:00:0040.043.9
gpt-5.4 + Google Custom Search2026-05-09 03:00:0035.039.1
claude-opus-4.62026-05-09 03:00:0030.035.5
llama-4-scout + Google Custom Search2026-05-09 03:00:0030.034.6
gemini-3.1-pro-preview + Google Custom Search2026-05-09 03:00:0030.032.4
claude-opus-4.6 + Google Custom Search2026-05-09 03:00:0025.034.1
claude-sonnet-4.6 + Google Custom Search2026-05-09 03:00:0025.032.7
llama-4-maverick + Google Custom Search2026-05-09 03:00:0025.030.3
gpt-5.3-chat2026-05-09 03:00:0025.029.5
gemini-3.1-pro-preview2026-05-09 03:00:0025.028.2
claude-sonnet-4.62026-05-09 03:00:0020.024.2
gpt-5.42026-05-09 03:00:0020.023.7
gemini-2.5-pro + Google Custom Search2026-05-09 03:00:0015.017.1
llama-4-maverick2026-05-09 03:00:0010.017.5
llama-4-scout2026-05-09 03:00:0010.015.2
gemini-2.5-pro2026-05-09 03:00:000.01.5

(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