Thanks to visit codestin.com
Credit goes to realtimeqa.github.io

Codestin Search App Codestin Search App Codestin Search App Codestin Search App Codestin Search App

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-3.5 Haiku + Google Custom Search2026-01-10 03:00:00100.070.0
GPT-4o + Google Custom Search2026-01-10 03:00:0090.070.0
GPT-4.1 + Google Custom Search2026-01-10 03:00:0090.070.0
GPT-4o2026-01-10 03:00:0090.060.0
Claude-3.7 Sonnet + Google Custom Search2026-01-10 03:00:0090.060.0
GPT-4.12026-01-10 03:00:0080.060.0
Claude-3.7 Sonnet2026-01-10 03:00:0070.050.0
Claude-3.5 Haiku2026-01-10 03:00:0060.040.0
Gemini 2.0 Flash + Google Custom Search2026-01-10 03:00:000.00.0
Gemini 2.0 Flash2026-01-10 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
Gemini 2.0 Flash + Google Custom Search2026-01-10 03:00:0040.046.3
GPT-4o + Google Custom Search2026-01-10 03:00:0020.030.4
Gemini 2.0 Flash2026-01-10 03:00:0020.020.0
GPT-4.1 + Google Custom Search2026-01-10 03:00:0010.022.7
GPT-4o2026-01-10 03:00:0010.018.9
GPT-4.12026-01-10 03:00:0010.018.9
Claude-3.7 Sonnet + Google Custom Search2026-01-10 03:00:000.013.9
Claude-3.5 Haiku2026-01-10 03:00:000.012.9
Claude-3.5 Haiku + Google Custom Search2026-01-10 03:00:000.012.4
Claude-3.7 Sonnet2026-01-10 03:00:000.010.8

(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