Google 🇺🇸 · LaMDA

LaMDA 137B

Google's 137-billion-parameter open-domain dialogue model evaluated for quality, safety, and groundedness.

DOOM SCORE21.4out 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 21.4

The model demonstrated strong open-domain dialogue capability but no consequential agency and minimal deployment at the original result date. Documented safety limitations create moderate misuse and control difficulty without implying autonomous operation.

Capability42
Autonomy2
Deployment3
Misuse potential24
Control difficulty22
MODEL-ATTRIBUTED EVIDENCE

News tied to LaMDA 137B

The model score of 21.4 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.

Capability TOWARD

Google publishes 137B LaMDA dialogue model

Google researchers published the 137-billion-parameter LaMDA dialogue model and its safety, quality, and groundedness evaluations; the model family later powered the public Bard service.

Full item contribution
+0.03
LaMDA 137B equal share
+0.03
Read assessment →
AUDIT TRAIL

Model score history

  1. R4
    Doom Score 21.4

    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 21.4

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

    12 Aug 2026
  3. R2
    Doom Score 23.9

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

    12 Aug 2026
  4. R1
    Doom Score 27.3

    New exact public Google model with distinct size, release timestamp, primary source, and five evidence-based dimension inputs.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for LaMDA 137B.
  1. LaMDA 137B by Google has a DoomBench model risk score of 21.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. LaMDA 137B's highest current DoomBench dimension is capability at 42.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to LaMDA 137B, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/google-lamda-137b