GPT-realtime
Real-time speech model with image input, asynchronous tools, remote MCP and telephony integration.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 73.9
Strong real-time multimodal interaction and external tool connectivity raise capability and autonomy; broad API and telephony access create near-maximal deployment, while closed hosting and safeguards moderate control difficulty.
News tied to GPT-realtime
The model score of 73.9 rates this model's risk profile. The overall Doom Index of 66.8 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
OpenAI releases GPT-realtime and general-availability Realtime API
OpenAI released GPT-realtime with speech-to-speech reasoning, image input, asynchronous function calls, remote MCP support and SIP connectivity as the Realtime API reached general availability.
- Full item contribution
- +0.12
- GPT-realtime equal share
- +0.12
Model score history
-
R4
Doom Score 73.9
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 73.9
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 73.7
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 73.3
New exact August 2025 model profile verified by OpenAI's launch and developer documentation.
12 Aug 2026