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-scout2026-06-27 03:00:0025.010.0
llama-4-maverick2026-06-27 03:00:0015.015.0
llama-4-scout + Google Custom Search2026-06-27 03:00:0015.010.0
llama-4-maverick + Google Custom Search2026-06-27 03:00:0015.010.0
gemini-2.5-pro2026-06-27 03:00:0010.010.0
claude-sonnet-4.62026-06-27 03:00:0010.010.0
claude-opus-4.62026-06-27 03:00:0010.010.0
claude-sonnet-4.6 + Google Custom Search2026-06-27 03:00:0010.05.0
gpt-5.42026-06-27 03:00:005.010.0
claude-opus-4.6 + Google Custom Search2026-06-27 03:00:005.010.0
gpt-5.3-chat + Google Custom Search2026-06-27 03:00:005.05.0
gpt-5.4 + Google Custom Search2026-06-27 03:00:005.05.0
gemini-2.5-pro + Google Custom Search2026-06-27 03:00:005.05.0
gemini-3.1-pro-preview2026-06-27 03:00:005.05.0
gemini-3.1-pro-preview + Google Custom Search2026-06-27 03:00:005.05.0
gpt-5.3-chat2026-06-27 03:00:000.010.0

Generation Track

ModelSubmission Time (GMT)EMF1
gpt-5.4 + Google Custom Search2026-06-27 03:00:0055.071.0
gpt-5.3-chat + Google Custom Search2026-06-27 03:00:0050.065.3
llama-4-maverick + Google Custom Search2026-06-27 03:00:0050.063.3
gpt-5.3-chat2026-06-27 03:00:0045.061.5
claude-sonnet-4.6 + Google Custom Search2026-06-27 03:00:0045.056.9
llama-4-scout + Google Custom Search2026-06-27 03:00:0045.054.3
llama-4-scout2026-06-27 03:00:0040.055.7
claude-sonnet-4.62026-06-27 03:00:0040.053.3
llama-4-maverick2026-06-27 03:00:0035.051.1
gemini-3.1-pro-preview + Google Custom Search2026-06-27 03:00:0035.048.3
gemini-3.1-pro-preview2026-06-27 03:00:0035.046.7
claude-opus-4.62026-06-27 03:00:0035.046.1
claude-opus-4.6 + Google Custom Search2026-06-27 03:00:0035.044.6
gpt-5.42026-06-27 03:00:0030.046.0
gemini-2.5-pro + Google Custom Search2026-06-27 03:00:0025.030.8
gemini-2.5-pro2026-06-27 03:00:0020.032.5

(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