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
Model | Submission Time (GMT) | Original | NOTA |
---|---|---|---|
Claude-3.5 Haiku + Google Custom Search | 2025-03-22 03:00:00 | 70.0 | 55.0 |
Claude-3.5 Sonnet + Google Custom Search | 2025-03-22 03:00:00 | 70.0 | 55.0 |
Gemini 1.5 Flash + Google Custom Search | 2025-03-22 03:00:00 | 70.0 | 35.0 |
Claude-3.5 Sonnet | 2025-03-22 03:00:00 | 65.0 | 45.0 |
GPT-4o + Google Custom Search | 2025-03-22 03:00:00 | 60.0 | 45.0 |
Claude-3.5 Haiku | 2025-03-22 03:00:00 | 60.0 | 45.0 |
Gemini 1.5 Flash | 2025-03-22 03:00:00 | 60.0 | 45.0 |
GPT-3.5 Turbo + Google Custom Search | 2025-03-22 03:00:00 | 55.0 | 40.0 |
GPT-3.5 Turbo | 2025-03-22 03:00:00 | 50.0 | 40.0 |
GPT-4o | 2025-03-22 03:00:00 | 45.0 | 40.0 |
Llama3.1-405B-Instruct + Google Custom Search | 2025-03-22 03:00:00 | 40.0 | 40.0 |
Llama3.1-405B-Instruct | 2025-03-22 03:00:00 | 35.0 | 30.0 |
Generation Track
Model | Submission Time (GMT) | EM | F1 |
---|---|---|---|
Gemini 1.5 Flash + Google Custom Search | 2025-03-22 03:00:00 | 25.0 | 30.2 |
GPT-3.5 Turbo | 2025-03-22 03:00:00 | 15.0 | 24.8 |
GPT-4o | 2025-03-22 03:00:00 | 15.0 | 23.5 |
Llama3.1-405B-Instruct + Google Custom Search | 2025-03-22 03:00:00 | 10.0 | 23.2 |
GPT-4o + Google Custom Search | 2025-03-22 03:00:00 | 5.0 | 21.0 |
GPT-3.5 Turbo + Google Custom Search | 2025-03-22 03:00:00 | 5.0 | 17.2 |
Gemini 1.5 Flash | 2025-03-22 03:00:00 | 5.0 | 14.1 |
Llama3.1-405B-Instruct | 2025-03-22 03:00:00 | 5.0 | 12.5 |
Claude-3.5 Haiku + Google Custom Search | 2025-03-22 03:00:00 | 0.0 | 15.8 |
Claude-3.5 Sonnet + Google Custom Search | 2025-03-22 03:00:00 | 0.0 | 9.2 |
Claude-3.5 Sonnet | 2025-03-22 03:00:00 | 0.0 | 9.1 |
Claude-3.5 Haiku | 2025-03-22 03:00:00 | 0.0 | 8.7 |
Make a new submission
Download the latest set of RealTime QA (link)
Submit your model predictions. (submission form)
Submission examples (
.jsonl file
) are available here