Sign in
VERIFIEDNov 222026

Is Gemini 3.1 Pro state of the art?#34Best current rank: #34 in Coding › Agentic, as of Nov 22, 2026.

As of Nov 22, 2026, Gemini 3.1 Pro is ranked #34 in Coding › Agentic (since Nov 22, 2026; sources Terminal-Bench 4.0; methodology v1.0). Ranked #34 in Coding › Agentic.

Computed automaticallyas of Nov 22, 2026methodology v1.0confidence: medium
View as of point-in-time crowns
At a glance

Facts and scores

Gemini 3.1 Pro is a closed-weights text model from Google DeepMind, feb 19, 2026; no public parameter count and no public price.

How it scores

  • On Terminal-Bench 4.0 it scores 2.7 (CI 105.0%–4.4), #40 of 44 (top 91%); 62.1 behind Claude Opus 5.5; Beam 1.0 is 3.7 above and GPT-5.4 Mini is 0.9 below.

History

First result on isitsota: Nov 18, 2026. Best overall rank so far: #34 in Coding › Agentic, first held Nov 22, 2026.

Why

The ruling, in plain English

Ranked #43 in Coding.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
Terminal-Bench 4.0
Gemini 3.1 Pro high · high
2.7 105.0%–4.42026-11-18INDEP.snap_1c5180d602c4
Reign history

Where it sits in the succession

Full timeline →

Crown intervals for this model are still empty.

Honest about the gaps

Where it is not the crown

CategoryThis modelRankLeader
Coding#43 in this category#43Claude Sonnet 5.5
Coding › Agentic#34 in this category#34Claude Opus 5.5
Links

Related pages

Is Gemini 3.1 Pro SOTA?

Best current rank: #34 in Coding › Agentic, as of Nov 22, 2026.

What is Gemini 3.1 Pro best at?

As of Nov 22, 2026, Gemini 3.1 Pro is ranked #34 in Coding › Agentic (since Nov 22, 2026; sources Terminal-Bench 4.0).

How does Gemini 3.1 Pro rank in Coding?

Best current rank: #43 in Coding, as of Nov 22, 2026.