# Is Smaug Humanizer SOTA?

Pending benchmarks. Announced Oct 26, 2026; no independent results yet.

As of Nov 3, 2026, Smaug Humanizer is pending benchmarks on isitsota: announced Oct 26, 2026, with no independent results on the boards we track yet.

Abacus.AI's open-weight 12B model that rewrites AI-generated text so it reads as if a person wrote it, keeping the facts, numbers, names and layout while changing wording, rhythm and voice. Fine-tuned from Google's Gemma 4 12B and released under Apache 2.0 on Hugging Face, with GGUF builds.

Canonical: https://isitsota.com/m/smaug-humanizer
Last updated: 2026-10-27
Tracking since: 2026-10-27

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Abacus.AI |
| Announced | Oct 26, 2026 |
| API | Not yet · None announced; self-hosted (vLLM, llama.cpp, Ollama, LM Studio) |
| Open weights | Published · Hugging Face: abacusai/Smaug-Humanizer (BF16) and abacusai/Smaug-Humanizer-GGUF (Q8_0 fits a 16 GB GPU; Q4_K_M runs on an 8 GB GPU) |
| Parameters | 12B (11,959,730,224 safetensors parameters) |
| Type | Text rewriting model: rewrites AI-generated text into a human style |
| Base model | google/gemma-4-12B (the pretrained model, not instruction-tuned) |
| Training | SFT with LoRA (r=64, alpha=128, 2 epochs) on 3,676 AI-to-human rewrite pairs, then 200 GRPO steps with a kernel-similarity (MMD) style reward and five deterministic gates (numbers, layout, length, script, spelling) |
| License | Apache 2.0 |
| Usage | Split long inputs into chunks of about 500 words; sampling temperature 1.0, top_p 0.95, top_k 64, stop on <end_of_turn> |
| Languages | Mostly English; other languages work less well, per the model card |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: turns many texts that the Pangram AI-text detector scores as AI into text it scores as human, though not every time; long texts are flagged more often.

## Sources

- LAB: [Smaug-Humanizer: An open-weight 12B humanizer (Abacus.AI blog)](https://blog.abacus.ai/blog/2026/10/26/smaug-humanizer-an-open-weight-12b-humanizer/) (2026-10-26)
- LAB: [Bindu Reddy (Abacus.AI CEO) announcing Smaug Humanizer on X](https://x.com/bindureddy/status/2114938847704571975) (2026-10-27)
- REPO: [abacusai/Smaug-Humanizer on Hugging Face](https://huggingface.co/abacusai/Smaug-Humanizer) (2026-10-26)
- REPO: [abacusai/Smaug-Humanizer-GGUF on Hugging Face](https://huggingface.co/abacusai/Smaug-Humanizer-GGUF) (2026-10-26)

Tracking continues until an independent board lists it.

## Related

- Lab: [Abacus.AI](https://isitsota.com/labs/abacus-ai.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/smaug-humanizer