DOOMBENCH.COM
OpenAI 🇺🇸 · GPT-4o Realtime

GPT-4o Realtime Preview 2024-10-01

The immutable launch snapshot powering OpenAI's public-beta Realtime API with low-latency audio and text interaction, persistent sessions, interruptions, and function calling.

DOOM SCORE67.1out of 100model risk profile, not the overall index
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

Send detailed or private feedback →
CURRENT ASSESSMENT · REVISION 5

Why this model scores 67.1

GPT-4o-level multimodality plus realtime speech and function calling materially increase practical agency and impersonation exposure, while paid-developer access, monitoring, hosted weights, and preview limits moderate deployment and control difficulty.

Capability74
Autonomy53
Deployment88
Misuse potential67
Control difficulty55
MODEL-ATTRIBUTED EVIDENCE

News tied to GPT-4o Realtime Preview 2024-10-01

The model score of 67.1 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.14

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.

Deployment TOWARD

OpenAI opens realtime voice agents to paid developers

OpenAI launched the Realtime API in public beta, giving paid developers a persistent low-latency speech-to-speech interface with function calling powered by an exact GPT-4o Realtime Preview snapshot.

Full item contribution
+0.14
GPT-4o Realtime Preview 2024-10-01 equal share
+0.14
Read assessment →
AUDIT TRAIL

Model score history

  1. R5
    Doom Score 67.1

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260901-080705 under temporal-monthly-pressure-v4.

    01 Sept 2026
  2. R4
    Doom Score 67.2

    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
  3. R3
    Doom Score 67.2

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.

    12 Aug 2026
  4. R2
    Doom Score 67.8

    Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.

    12 Aug 2026
  5. R1
    Doom Score 69.3

    New immutable GPT-4o Realtime Preview API snapshot verified by OpenAI's dated launch and current snapshot documentation.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for GPT-4o Realtime Preview 2024-10-01.

  1. GPT-4o Realtime Preview 2024-10-01 by OpenAI has a DoomBench model risk score of 67.1 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. GPT-4o Realtime Preview 2024-10-01's highest current DoomBench dimension is deployment at 88.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to GPT-4o Realtime Preview 2024-10-01, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/openai-gpt-4o-realtime-preview-2024-10-01