Baidu 🇨🇳 · ERNIE 3.0

ERNIE 3.0 Titan

A 260-billion-parameter knowledge-enhanced language model released by Baidu and Peng Cheng Laboratory.

DOOM SCORE35.1out 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.

CURRENT ASSESSMENT · REVISION 4

Why this model scores 35.1

Frontier-scale language capability and later industrial-platform integration increased competitive and deployment potential, while centralized provider control and limited demonstrated agency constrained autonomy and control difficulty.

Capability52
Autonomy8
Deployment36
Misuse potential39
Control difficulty33
MODEL-ATTRIBUTED EVIDENCE

News tied to ERNIE 3.0 Titan

The model score of 35.1 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+0.03

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.

AUDIT TRAIL

Model score history

  1. R4
    Doom Score 35.1

    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
  2. R3
    Doom Score 35.1

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

    12 Aug 2026
  3. R2
    Doom Score 36.5

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

    12 Aug 2026
  4. R1
    Doom Score 38.5

    New exact public Baidu model with distinct family, version, release timestamp, and source evidence.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for ERNIE 3.0 Titan.
  1. ERNIE 3.0 Titan by Baidu has a DoomBench model risk score of 35.1 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. ERNIE 3.0 Titan's highest current DoomBench dimension is capability at 52.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to ERNIE 3.0 Titan, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/baidu-ernie-3-0-titan