GS1-9B

Fast, Faithful, Frontier System One Intelligence.

Code · Model · Documentation · Playground

GS1 is a family of open-source decision models developed by BIGAI (Beijing Institute for General Artificial Intelligence). It computes native probability distributions over runtime-defined candidates for agent routing, verification, extraction and control.

GS1 Highlights

• Fast - Native Runtime Decision Head.
  • Produce Choice, Noul and Score distributions directly, with zero generated output tokens.
  • A native multi-head cross-attention decision head queries state evidence using question and candidate representations.
  • Within the GS1 family, CUDA Graph lets GS1-0.8B reach 12.51 ms P50 for one short question and 6.05× speedup over default inference for eight short questions.
• Faithful — multi-step RL with calibrated rewards
  • Reinforcement learning optimizes sampled action probabilities with a Brier reward. RLCD
  • Native probabilities and confidence support evidence gathering, deferral and explicit abstention choices.
• Frontier — Hybrid Architecture, Competitive Quality
  • Causal Gated DeltaNet and Segmented Bidirectional Full Attention give candidates their complete comparison context while preserving immutable prefixes for reuse across questions.
  • Carry-preserving Attention Residual lets sparse full-attention receivers query earlier representations while retaining the explicit skip-connection anchor. Architecture
  • GS1-9B reaches 70.45 on the latest Decision Index 0.4.1 Public index. All GS1 sizes lie on the displayed parameter–performance frontier.

Model Overview

Specification	GS1-9B
Model type	Native typed decision model
Stored parameters	8,829,078,768
Hidden dimension	4,096
Decoder layers	32
Decision attention heads	16
Candidate-routing layers	2
Decision projection dimension	2,048
Maximum complete branch length	32,768 tokens

GS1 uses a Qwen3.5 hybrid backbone that interleaves three causal Gated DeltaNet layers with one segmented full-attention layer. A native cross-attention decision head compares runtime-defined candidates against state evidence. Architecture

Text and decision-head weights are stored in FP32, and the retained vision tower in BF16. Inference supports BF16 computation with FP32 final logits and probability reductions. Stored dtypes are preserved by default loading.

Primitive	Typical use	Output
Choice	Routing, classification, tool selection	Candidate ID, all candidate probabilities, confidence
Noul	Verification and binary judgments	Probability that the proposition is true: p(true)
Score	Ordered ratings and rubric judgments	Expected zero-based level, level probabilities, confidence

Benchmark Results

Decision Index

The following are the latest complete public-suite results (edition 0.3). Each model completes 140,178 requests and 312,320 decisions across 43 text benchmarks, with 100% coverage and zero failed or unsupported requests. 37 benchmarks contribute to the chance-corrected Public index; six additional benchmarks are displayed separately. The private Full score is evaluated by the leaderboard maintainers.

Metric	GS1-0.8B	GS1-2B	GS1-4B	GS1-9B
Public index ↑	56.12	62.22	68.97	70.45
Raw index ↑	67.36	71.70	76.47	77.46
Coverage	100%	100%	100%	100%

The frontier refers to the comparison models displayed in the figure.

Area Scores

Chance-corrected area scores on a 0–100 scale; higher is better.

Area	GS1-0.8B	GS1-2B	GS1-4B	GS1-9B
Knowledge & Reasoning	33.32	41.84	52.40	56.01
Language Understanding	56.25	63.67	71.12	72.62
Retrieval & Classification	68.62	71.21	75.55	75.58
Tools & Automation	79.26	83.57	87.49	87.61
Arts & Human Taste	47.47	54.16	59.26	60.57

Complete text benchmark results — 43 benchmarks

Native benchmark scores are scaled to 0–100 before chance correction. The metric is shown for each row. † marks the six display-only benchmarks that do not contribute to the Public index. All rows use the Decision Index typed-decision protocol.

Benchmark	Native metric	GS1-0.8B	GS1-2B	GS1-4B	GS1-9B
BFCL	case exact accuracy	90.44	93.27	97.52	96.99
ToolRet	nDCG@10	67.52	69.25	71.16	70.90
API-Bank	accuracy	67.52	76.97	84.45	85.43
BANKING77	macro-F1	85.33	88.34	92.09	92.76
CLINC150+OOS	macro-F1	85.51	90.61	94.35	93.48
RouterBench †	selected quality (quality objective)	79.63	71.76	79.06	79.86
Home appliance simulator	case exact accuracy	98.86	100.00	100.00	100.00
SGD/SGD-X †	macro-F1	61.15	65.16	68.10	67.60
ContractNLI	macro-F1	84.41	84.14	85.99	86.16
ANLI	macro-F1	58.98	65.80	75.74	77.32
BPoMP	accuracy	78.14	87.24	92.02	93.92
Humicroedit	accuracy	61.80	62.56	65.68	64.50
POP909-CL	accuracy	84.40	84.95	84.70	85.05
cfcolor	accuracy	69.02	68.70	71.26	71.38
MMLU †	accuracy	56.09	65.65	77.95	81.42
GPQA Diamond	accuracy	33.67	35.71	44.39	48.47
ARC-Easy †	accuracy	88.97	95.50	98.19	98.82
ARC-Challenge †	accuracy	78.16	87.54	95.05	96.08
WinoGrande	accuracy	71.11	80.82	89.66	92.74
HellaSwag	accuracy	80.85	89.44	94.81	96.28
GSM8K	accuracy	49.47	57.35	69.37	71.04
ChessBench	accuracy	25.44	26.24	28.60	29.08
MuSR	accuracy	62.10	70.08	71.94	74.60
SATA-Bench	case exact accuracy	46.48	53.33	54.61	55.70
SimpleBench †	accuracy	0.00	10.00	0.00	10.00
BRIGHT	nDCG@10	37.32	38.75	46.58	45.40
Amazon ESCI	macro-F1	56.30	57.51	60.69	61.48
ACOS	per-review F1	51.22	52.45	56.19	56.93
FinEntity	macro-F1	85.65	87.77	95.53	94.83
iSarcasmEval	Sarcasm F1 · track A, English	44.64	59.44	63.76	68.02
VAST	macro-F1	76.52	77.34	78.62	78.49
NLI4CT	macro-F1	66.64	73.41	80.38	82.39
CRUXEval	accuracy	42.98	57.89	78.60	81.40
CLadder	accuracy	89.44	87.74	91.30	94.82
HLE	accuracy	14.97	13.97	11.98	11.58
Habermas Machine	accuracy	56.80	59.13	61.93	63.13
PhishNChips phishing decisions	accuracy	98.20	97.85	99.30	98.90
MMLU-Pro	accuracy	38.66	47.10	60.51	64.06
BBH fixed-option tasks	accuracy	68.88	76.96	84.07	87.07
RAGTruth response-level hallucination	F1 on hallucinated class	79.96	83.00	85.20	85.08
HoVer claim verification	accuracy	85.85	88.10	89.15	90.05
When2Call MCQ	accuracy	86.39	89.40	91.59	92.06
New Yorker caption matching	accuracy	56.25	65.91	73.67	76.52

Evaluation uses BF16 native reference inference and the official scorer. Independent re-scoring of the compressed predictions reproduces the results exactly.

Inference Performance

Latest family measurements for the 256-token, single-question fixture:

Model	GS1 Default P50 (ms)	CUDA Graph P50 / P95 (ms)	Speedup	Graph allocated (GiB)
GS1-0.8B	54.10	12.51 / 13.22	4.32×	4.07
GS1-2B	53.95	18.64 / 18.69	2.89×	10.60
GS1-4B	72.87	35.17 / 35.24	2.07×	23.68

Single RTX 4090 reporting 48 GiB, BF16 computation, five warmups and 30 timed calls per group. Timing covers the complete in-process decision call, including validation, prompt compilation, model execution, probabilities and typed responses; model loading, graph capture, HTTP and SDK transport are excluded. Speedup compares GS1 Default P50 with CUDA Graph P50 using identical weights and inputs. Latency and memory depend on request shape.

Quickstart

Hugging Face Transformers

Use Python 3.11+ and install the dependencies:

python -m pip install torch==2.9.1 torchvision==0.24.1 transformers==5.3.0 accelerate safetensors 'pydantic>=2.8,<3' typesafe-sdk==0.7.0 pillow

Load the Hub ID or a local model directory and submit all three decision primitives in one call:

import torch
from transformers import AutoModel

model = AutoModel.from_pretrained(
    "bigai/GS1-9B",
    trust_remote_code=True,
).eval().to("cuda")

request = {
    "state": "A customer was charged twice and requests an urgent refund.",
    "questions": {
        "team": {
            "type": "choice",
            "instructions": "Which team should handle this ticket?",
            "criteria": {
                "billing": "Payments and refunds",
                "technical": "Software problems"
            }
        },
        "refund": {
            "type": "noul",
            "instructions": "Does the customer request a refund?"
        },
        "urgency": {
            "type": "score",
            "instructions": "Rate the urgency of handling this ticket.",
            "criteria": [
                "Routine",
                "Soon",
                "Immediate"
            ]
        }
    }
}

with torch.autocast("cuda", dtype=torch.bfloat16, cache_enabled=False):
    result = model.decide(**request, precision="bf16")

print(result["answers"])
print(result["usage"])

The response contains model, answers and usage. Choice preserves candidate IDs and returns every candidate probability; Noul returns p(true); Score returns the expected zero-based rubric level and its full probability distribution. Generated output_tokens is zero.

chat_template.jinja renders the native GS1 state, question and options, including XML escaping, the trained user/assistant boundaries, the empty thinking prefix and <|decide|>. It is exported from the same serializer in compiler.py. model.decide prepares typed candidates, branch spans, masks, positions and budget checks. Native template usage

GS1 Runtime

The GS1 runtime adds shared-state reuse, compatible batching, HTTP serving and qualified CUDA Graph replay:

git clone https://github.com/bigai-nlco/GS1.git
cd GS1
uv sync --locked --extra serve --extra cuda
uv run gs1 serve --model bigai/GS1-9B --model-name GS1

The service exposes POST /v1/systemone and GET /v1/models at http://127.0.0.1:8000. The Playground provides an interactive Query workspace.

TypeSafe SDK

Call the running service through the official SDK:

from typesafe_sdk import Choice, Noul, Score, TypeSafeClient

with TypeSafeClient(
    base_url="http://127.0.0.1:8000", api_key="local", model="GS1",
) as client:
    result = client.system_one(
        state="A customer was charged twice and requests an urgent refund.",
        questions={
            "team": Choice(
                instructions="Which team should handle this ticket?",
                criteria={"billing": "Payments and refunds", "technical": "Software problems"},
            ),
            "refund": Noul(instructions="Does the customer request a refund?"),
            "urgency": Score(
                instructions="Rate the urgency of handling this ticket.",
                criteria=["Routine", "Soon", "Immediate"],
            ),
        },
    )

print(result.choices["team"].choice)
print(result.choices["team"].probabilities)
print(result.nouls["refund"].noul)
print(result.scores["urgency"].score)

Use the API root as base_url and match model to the server alias configured by --model-name. The SDK accepts api_key="local" for this local service.

License

Code and released model weights use Apache-2.0.

Citation

If you find our work helpful, feel free to give us a cite.

@techreport{zheng2026gs1,
  title={GS1: Fast, Faithful, Frontier System One Intelligence},
  author={Zheng, Zilong and Liu, Yang and Qin, Shuhan and Lin, Ziyong and Li, Jiaqi and Jia, Zixia and Zhu, Song-Chun},
  institution={BIGAI},
  year={2026}
}