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-4.1 + Google Custom Search2026-02-07 03:00:0026.76.7
gpt-4.12026-02-07 03:00:0013.36.7
claude-sonnet-4.52026-02-07 03:00:006.713.3
claude-sonnet-4.5 + Google Custom Search2026-02-07 03:00:006.713.3
llama-4-scout + Google Custom Search2026-02-07 03:00:006.76.7
llama-4-maverick + Google Custom Search2026-02-07 03:00:006.76.7
gpt-5.2 + Google Custom Search2026-02-07 03:00:006.70.0
claude-haiku-4.5 + Google Custom Search2026-02-07 03:00:006.70.0
gemini-2.5-pro + Google Custom Search2026-02-07 03:00:000.06.7
claude-haiku-4.52026-02-07 03:00:000.06.7
llama-4-scout2026-02-07 03:00:000.06.7
gpt-5.22026-02-07 03:00:000.00.0
gemini-2.5-pro2026-02-07 03:00:000.00.0
gemini-3-pro-preview2026-02-07 03:00:000.00.0
gemini-3-pro-preview + Google Custom Search2026-02-07 03:00:000.00.0
llama-4-maverick2026-02-07 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
claude-sonnet-4.52026-02-07 03:00:0046.760.0
llama-4-maverick + Google Custom Search2026-02-07 03:00:0046.760.0
llama-4-maverick2026-02-07 03:00:0046.757.3
gemini-3-pro-preview2026-02-07 03:00:0046.752.0
gpt-5.2 + Google Custom Search2026-02-07 03:00:0040.061.4
gpt-4.12026-02-07 03:00:0040.056.0
llama-4-scout2026-02-07 03:00:0040.053.3
gpt-5.22026-02-07 03:00:0040.050.7
llama-4-scout + Google Custom Search2026-02-07 03:00:0040.045.3
gemini-2.5-pro2026-02-07 03:00:0033.347.9
claude-haiku-4.52026-02-07 03:00:0033.339.3
claude-haiku-4.5 + Google Custom Search2026-02-07 03:00:0033.338.2
gemini-3-pro-preview + Google Custom Search2026-02-07 03:00:0033.336.0
gpt-4.1 + Google Custom Search2026-02-07 03:00:0026.753.3
claude-sonnet-4.5 + Google Custom Search2026-02-07 03:00:0013.318.7
gemini-2.5-pro + Google Custom Search2026-02-07 03:00:0013.313.3

(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