Is H2O Lightning 31B v1.3.0 state of the art?#19Best current rank: #19 in Decision models, as of Nov 22, 2026.
As of Nov 22, 2026, H2O Lightning 31B v1.3.0 is ranked #19 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Ranked #19 in Decision models.
Facts and scores
H2O Lightning 31B v1.3.0 is an open-weights text model from H2O.ai; 31B parameters and no public price.
How it scores
- On Decision Index Full it scores 69.9 (CI 69.4–70.4), #22 of 420 (top 6%); 4.0 behind karpo-decision-31B; Bespoke Nimble v4.1 Max (27B) is 0.1 above and Jeffan-31b-1710 is 0.1 below.
- On Decision Index Brier it scores 28.4%, #55 of 419 (top 14%); 8.0 pts behind lg-decision-4B; level with OneJev1.6-9B above and level with torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune) below.
- On Decision Index ECE it scores 4.0%, #91 of 420 (top 22%); 2.9 pts behind KnowLine 9B Gen2; level with Blink v0.3 26B-A4B (NVFP4) above and level with PKU-KCL-Meteor-2B v1.5 below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #19 in Decision models, first held Nov 22, 2026.
Reliability
Index bins for H2O Lightning 31B v1.3.0. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 135.3 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full H2O Lightning 31B v1.3.0 | 69.9 69.4–70.4 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Decision models | #19 in this category | #19 | karpo-decision-31B |
Related pages
- Decision models
- Compare with the current leader in Decision models: karpo-decision-31B
- Compare with the current leader in Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
- Compare with the current leader in Decision models: GLiDE 27B
- Compare with the current leader in Decision models: kudhab (Gemma 4 31B)
- H2O Lightning 31B v1.3.0 vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- H2O Lightning 31B v1.3.0 vs REAX 1.3
- H2O Lightning 31B v1.3.0 vs Logits Sigma-1 Duo
- Decision Index Full
- Decision Index latency
- Lab: H2O.ai
Is H2O Lightning 31B v1.3.0 SOTA?
Best current rank: #19 in Decision models, as of Nov 22, 2026.
What is H2O Lightning 31B v1.3.0 best at?
As of Nov 22, 2026, H2O Lightning 31B v1.3.0 is ranked #19 in Decision models (since Nov 22, 2026; sources Decision Index Full).