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-4.62026-07-18 03:00:0015.010.0
claude-sonnet-4.6 + Google Custom Search2026-07-18 03:00:0015.05.0
gpt-5.4 + Google Custom Search2026-07-18 03:00:0010.015.0
claude-opus-4.6 + Google Custom Search2026-07-18 03:00:0010.010.0
llama-4-maverick + Google Custom Search2026-07-18 03:00:0010.010.0
claude-opus-4.62026-07-18 03:00:0010.05.0
llama-4-scout2026-07-18 03:00:005.020.0
gpt-5.3-chat2026-07-18 03:00:005.015.0
gpt-5.42026-07-18 03:00:005.015.0
gpt-5.3-chat + Google Custom Search2026-07-18 03:00:005.010.0
gemini-3.1-pro-preview2026-07-18 03:00:005.05.0
llama-4-scout + Google Custom Search2026-07-18 03:00:005.05.0
llama-4-maverick2026-07-18 03:00:000.020.0
gemini-2.5-pro2026-07-18 03:00:000.05.0
gemini-3.1-pro-preview + Google Custom Search2026-07-18 03:00:000.05.0
gemini-2.5-pro + Google Custom Search2026-07-18 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
gpt-5.3-chat + Google Custom Search2026-07-18 03:00:0035.041.2
gemini-3.1-pro-preview + Google Custom Search2026-07-18 03:00:0035.037.0
gpt-5.3-chat2026-07-18 03:00:0030.043.9
claude-opus-4.62026-07-18 03:00:0025.033.3
gemini-3.1-pro-preview2026-07-18 03:00:0025.031.2
gpt-5.42026-07-18 03:00:0025.030.4
llama-4-scout2026-07-18 03:00:0025.030.0
gpt-5.4 + Google Custom Search2026-07-18 03:00:0025.029.6
llama-4-scout + Google Custom Search2026-07-18 03:00:0025.029.3
llama-4-maverick + Google Custom Search2026-07-18 03:00:0020.029.2
claude-sonnet-4.62026-07-18 03:00:0020.026.6
claude-sonnet-4.6 + Google Custom Search2026-07-18 03:00:0020.026.0
llama-4-maverick2026-07-18 03:00:0015.026.0
claude-opus-4.6 + Google Custom Search2026-07-18 03:00:0015.021.8
gemini-2.5-pro + Google Custom Search2026-07-18 03:00:0015.019.0
gemini-2.5-pro2026-07-18 03:00:0010.010.8

(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