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-3.5 Haiku2025-09-13 03:00:0060.050.0
GPT-4.1 + Google Custom Search2025-09-13 03:00:0050.050.0
GPT-4o + Google Custom Search2025-09-13 03:00:0050.040.0
Claude-3.7 Sonnet + Google Custom Search2025-09-13 03:00:0050.040.0
GPT-4o2025-09-13 03:00:0050.030.0
Claude-3.5 Haiku + Google Custom Search2025-09-13 03:00:0050.030.0
GPT-4.12025-09-13 03:00:0040.040.0
Claude-3.5 Sonnet + Google Custom Search2025-09-13 03:00:0040.040.0
Claude-3.5 Sonnet2025-09-13 03:00:0040.020.0
Claude-3.7 Sonnet2025-09-13 03:00:0040.020.0
Gemini 1.5 Flash + Google Custom Search2025-09-13 03:00:000.00.0
Gemini 1.5 Flash2025-09-13 03:00:000.00.0
Gemini 2.0 Flash + Google Custom Search2025-09-13 03:00:000.00.0
Gemini 2.0 Flash2025-09-13 03:00:000.00.0

Generation Track

ModelSubmission Time (GMT)EMF1
Gemini 2.0 Flash2025-09-13 03:00:0010.021.2
Claude-3.7 Sonnet + Google Custom Search2025-09-13 03:00:000.014.3
GPT-4o2025-09-13 03:00:000.012.7
GPT-4.12025-09-13 03:00:000.011.1
Gemini 2.0 Flash + Google Custom Search2025-09-13 03:00:000.011.1
Claude-3.5 Haiku + Google Custom Search2025-09-13 03:00:000.010.9
Gemini 1.5 Flash2025-09-13 03:00:000.010.0
Claude-3.5 Sonnet + Google Custom Search2025-09-13 03:00:000.09.9
GPT-4.1 + Google Custom Search2025-09-13 03:00:000.09.3
GPT-4o + Google Custom Search2025-09-13 03:00:000.09.3
Gemini 1.5 Flash + Google Custom Search2025-09-13 03:00:000.08.7
Claude-3.5 Haiku2025-09-13 03:00:000.08.2
Claude-3.5 Sonnet2025-09-13 03:00:000.08.1
Claude-3.7 Sonnet2025-09-13 03:00:000.08.1

(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