FlexDM-LoRA 2.1 · Gemma-4-31B vs Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
As of Nov 22, 2026, FlexDM-LoRA 2.1 · Gemma-4-31B leads Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) in 0 of 1 shared categories.
FlexDM-LoRA 2.1 · Gemma-4-31B
Close. Near-SOTA in Decision models, rank #10.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Yes. SOTA in Decision models (tied).
| Category | FlexDM-LoRA 2.1 · Gemma-4-31B | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) |
|---|---|---|
| Decision models | #10 · Near-SOTA · Decision models Margin 2.608695652173921 Jev Decision Index · Nov 21, 2026 | #1 · Co-SOTA · Decision models Margin 0 JevBench · Oct 8, 2026 |
Pricing
FlexDM-LoRA 2.1 · Gemma-4-31B: price per 1M tokens is unset in the catalog.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout): price per 1M tokens is unset in the catalog.
FlexDM-LoRA 2.1 · Gemma-4-31B: open weights.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout): open weights.
Benchmarks side by side
| Benchmark | FlexDM-LoRA 2.1 · Gemma-4-31B | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) |
|---|---|---|
| Decision Index Brier | 30.5% | 33.5% |
| Decision Index ECE | 5.4% | 7.1% |
| Decision Index Full | 71.6 | 62.8 |
| Decision Index latency | 155 | 104 |
Latest validated result for each model. Benchmarks where only one model has a result are left out.
Verdict
As of Nov 22, 2026, FlexDM-LoRA 2.1 · Gemma-4-31B leads Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) in 0 of 1 shared categories.
Decision models: As of Nov 22, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads FlexDM-LoRA 2.1 · Gemma-4-31B in Decision models at #1 against #10.
FlexDM-LoRA 2.1 · Gemma-4-31B · Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
FlexDM-LoRA 2.1 · Gemma-4-31B or Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)?
As of Nov 22, 2026, FlexDM-LoRA 2.1 · Gemma-4-31B leads Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) in 0 of 1 shared categories.
FlexDM-LoRA 2.1 · Gemma-4-31B or Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) for Decision models?
As of Nov 22, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads FlexDM-LoRA 2.1 · Gemma-4-31B in Decision models at #1 against #10.