Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) vs Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
As of Oct 14, 2026, Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) leads Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) in 0 of 1 shared categories.
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted)
#23 Best current rank: #23 in Decision models, as of Oct 14, 2026.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Yes. SOTA in co-SOTA in Decision models.
| Category | Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) |
|---|---|---|
| Decision models | #23 · #23 in Decision models Margin 10.606060606060609 JevBench · Oct 8, 2026 | #1 · Co-SOTA · Decision models Margin 0 Jev Decision Index · Oct 14, 2026 |
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted): 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.
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted): open weights.
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout): open weights.
Decision models: As of Oct 14, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) in Decision models at #1 against #23.
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) · Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) or Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)?
As of Oct 14, 2026, Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) leads Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) in 0 of 1 shared categories.
Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) or Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) for Decision models?
As of Oct 14, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) leads Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted) in Decision models at #1 against #23.