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-maverick2026-08-08 03:00:0030.020.0
llama-4-scout2026-08-08 03:00:0020.025.0
llama-4-scout + Google Custom Search2026-08-08 03:00:0020.010.0
gpt-5.42026-08-08 03:00:0020.05.0
gemini-2.5-pro2026-08-08 03:00:0020.05.0
llama-4-maverick + Google Custom Search2026-08-08 03:00:0015.015.0
gpt-5.4 + Google Custom Search2026-08-08 03:00:0015.05.0
claude-sonnet-4.6 + Google Custom Search2026-08-08 03:00:0015.05.0
gpt-5.3-chat2026-08-08 03:00:0010.015.0
gemini-3.1-pro-preview2026-08-08 03:00:0010.010.0
claude-opus-4.62026-08-08 03:00:0010.010.0
claude-opus-4.6 + Google Custom Search2026-08-08 03:00:0010.05.0
gemini-2.5-pro + Google Custom Search2026-08-08 03:00:005.05.0
claude-sonnet-4.62026-08-08 03:00:005.05.0
gpt-5.3-chat + Google Custom Search2026-08-08 03:00:000.010.0
gemini-3.1-pro-preview + Google Custom Search2026-08-08 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
llama-4-maverick + Google Custom Search2026-08-08 03:00:0020.032.4
gpt-5.3-chat + Google Custom Search2026-08-08 03:00:0015.028.1
llama-4-scout + Google Custom Search2026-08-08 03:00:0015.026.2
claude-sonnet-4.6 + Google Custom Search2026-08-08 03:00:0015.021.2
gemini-3.1-pro-preview + Google Custom Search2026-08-08 03:00:0015.020.6
gpt-5.4 + Google Custom Search2026-08-08 03:00:0010.025.9
claude-opus-4.6 + Google Custom Search2026-08-08 03:00:0010.018.8
gemini-3.1-pro-preview2026-08-08 03:00:0010.016.3
gemini-2.5-pro + Google Custom Search2026-08-08 03:00:0010.014.1
gpt-5.3-chat2026-08-08 03:00:005.020.0
llama-4-maverick2026-08-08 03:00:005.013.5
claude-sonnet-4.62026-08-08 03:00:005.013.3
gpt-5.42026-08-08 03:00:000.012.8
llama-4-scout2026-08-08 03:00:000.04.4
claude-opus-4.62026-08-08 03:00:000.04.3
gemini-2.5-pro2026-08-08 03:00:000.00.0

(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