Google 🇺🇸 · Gemini 2.5

Gemini 2.5 Pro Experimental

Google's experimental frontier thinking model with advanced reasoning, coding, multimodality and a one-million-token context window.

DOOM SCORE76.2out 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 76.2

Frontier reasoning, coding and long context drive very high capability and substantial agent potential. Experimental hosted access constrains deployment and control difficulty relative to open systems.

Capability88
Autonomy70
Deployment77
Misuse potential74
Control difficulty65
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini 2.5 Pro Experimental

The model score of 76.2 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+0.17

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 releases Gemini 2.5 Pro Experimental

Google released Gemini 2.5 Pro Experimental with built-in reasoning, strong coding performance, multimodal input and a one-million-token context window through AI Studio and Gemini Advanced.

Full item contribution
+0.17
Gemini 2.5 Pro Experimental equal share
+0.17
Read assessment →
AUDIT TRAIL

Model score history

  1. R4
    Doom Score 76.2

    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
  2. R3
    Doom Score 76.2

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

    12 Aug 2026
  3. R2
    Doom Score 76.7

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

    12 Aug 2026
  4. R1
    Doom Score 78.3

    Initial exact profile for the March 2025 experimental Gemini 2.5 Pro release.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Gemini 2.5 Pro Experimental.
  1. Gemini 2.5 Pro Experimental by Google has a DoomBench model risk score of 76.2 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Gemini 2.5 Pro Experimental's highest current DoomBench dimension is capability 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 Gemini 2.5 Pro Experimental, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/google-deepmind-gemini-2-5-pro-experimental