Sign in
VERIFIEDNov 222026

Is Hopper 12B Trained state of the art?#120Best current rank: #120 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, Hopper 12B Trained is ranked #120 in Decision models (since Nov 22, 2026; sources JevBench; methodology v1.0). Ranked #120 in Decision models.

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

Facts and scores

Hopper 12B Trained is an open-weights (apache-2.0) text model from HopitAI; 12B parameters and no public price.

How it scores

  • On JevBench it scores 68.1 (CI 67.6–68.6), #37 of 134 (top 28%); 14.7 behind Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout); JevOne is 0.8 above and level with SPX-CD-Omni (SurdAI, google/gemma-4-12B-it + LoRA r32, one forward pass, self-hosted) below.
  • On JevBench price it scores 2.9%, #76 of 134 (top 57%); 2.8 pts behind verdict-small (Manavarya09, multilingual-e5-small 118M); torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) is 0.1 pts above and level with Jev-Omni (akhilaaa3, Gemma-4-12B merged) below.

History

First result on isitsota: Oct 8, 2026. Best overall rank so far: #120 in Decision models, first held Nov 22, 2026.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
JevBench
Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted)
68.1 67.6–68.62026-10-08INDEP.snap_jevbench_2026-10-08_v1.6.1|jevbench-v1.6.1
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
Decision models#120 in this category#120karpo-decision-31B
Links

Related pages

Is Hopper 12B Trained SOTA?

Best current rank: #120 in Decision models, as of Nov 22, 2026.

What is Hopper 12B Trained best at?

As of Nov 22, 2026, Hopper 12B Trained is ranked #120 in Decision models (since Nov 22, 2026; sources JevBench).