Instructions to use FINAL-Bench/Darwin-180B-RSI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-180B-RSI with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="FINAL-Bench/Darwin-180B-RSI")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-180B-RSI")
model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-180B-RSI", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Darwin-180B-RSI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-180B-RSI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-180B-RSI

SGLang

How to use FINAL-Bench/Darwin-180B-RSI with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FINAL-Bench/Darwin-180B-RSI" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FINAL-Bench/Darwin-180B-RSI" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-180B-RSI with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-180B-RSI
```

Darwin-180B-RSI

180B Mixture-of-Experts · vision-language · #1 on five Hugging Face official leaderboards — AIME 2026 100 · HMMT Feb 2026 100 · GPQA Diamond 94.44 · MMLU-Pro 88.12 · MMMU-Pro 79.48 · self-improving

reasoning · MoE 512 experts · 262K long context · image + text · Korean + English · self-improvement · ZTC

The newest flagship of the Darwin family — #1 on AIME 2026, HMMT Feb 2026, GPQA Diamond, MMLU-Pro and MMMU-Pro, and a model that gets better by learning from its own verified work.

🏆 Five #1s — head-to-head with Chinese frontier models

Scores as listed on the Hugging Face official benchmark leaderboards (self-reported by each model's publisher). 🥇 = #1 on that leaderboard. "—" = not reported.

Model	AIME 2026	GPQA Diamond	MMLU-Pro	MMMU-Pro	HMMT Feb 2026
🧬 Darwin-180B-RSI (ours · 🇰🇷)	100 🥇	94.44 🥇	88.12 🥇	79.48 🥇	100 🥇
Kimi-K3 (Moonshot AI)	—	93.5	—	—	—
Kimi-K2.6 (Moonshot AI)	96.4	90.5	—	79.4	92.7
DeepSeek-V4-Pro (DeepSeek)	—	90.1	87.5	—	—
Qwen3.5-397B-A17B (Alibaba)	93.33	88.4	87.8	—	87.88
MiniMax-M2.1 (MiniMax)	—	80.81	88	—	—
GLM-5 (Zhipu AI)	95.83	86	86	—	86.36
Intern-S2-Preview (Shanghai AI Lab)	—	—	88	76.88	87.31
Step-3.5-Flash (StepFun)	96.67	83.5	84.4	—	86.36

_{Leaderboard values are each publisher's own reported numbers; settings (samples, voting, thinking budget) differ across models. Darwin-180B-RSI settings are listed in the evaluation protocol below.}

🧬 The Darwin Family

Darwin is VIDRAFT's measurement-driven reasoning model family — 50+ official models, 400+ community derivatives, and now two places in the GPQA Diamond top 3 (Darwin-180B-RSI #1 · Darwin-397B-ZTC #3).

🧬 Darwin — evolve the parent, keep what works

Darwin treats a strong open model as a parent. It measures where the parent is weak, and strengthens exactly those parts — instead of re-training everything and risking what already works.

Diagnose before you change. Every Darwin generation starts from a measured weakness map of the parent.
Change little, precisely. Darwin modifies a small, targeted fraction of the network. Knowledge stored in the experts is preserved.
Proven capability over new guesses. Earlier Darwin generations grafted the best-performing expert/FFN blocks from other strong models onto a base backbone; Darwin-180B-RSI adds a new ingredient — the model's own verified work.
Measured, not claimed. Every change must beat the parent on held-out tests before it ships.

Model	Scale	GPQA Diamond
Darwin-9B-NEG	9B	84.3
Darwin-27B-Opus	27B dense	86.9
Darwin-36B-Opus	36B MoE	88.4
Darwin-28B-REASON	28B + DELPHI	89.39
Darwin-397B-ZTC	397B MoE (FP8)	93.43
Darwin-180B-RSI	180B MoE	94.44

Lineage

Role
Parent	`Qwen/Qwen3.8-Flash-Next`	180B MoE vision-language backbone · Qwen Community License 1.0
Darwin RSI	self-improvement on verified answers	the parent's own solutions, checked against verifiable answer keys, fed back as training signal
Preserved	512 routed experts · router · vision encoder	untouched — the parent's knowledge stays intact
ZTC	zero-token confidence readout	see below

📄 Darwin Platform & Research

Darwin Family — MRI trust-weighted evolutionary merging for training-free scaling of language-model reasoning (arXiv:2605.14386)
Placement Is Free, Composition Is Not — the Latin square as a provably-balanced construction for heterogeneous sequence-mixer stacks (2609.20269) — the AETHER architecture line
FINAL Bench — VIDRAFT's measurement-driven evaluation framework (SSRN)
Four-layer Pre-AGI roadmap — Darwin → AETHER → PROMETHEUS → HEPHAESTUS
Collections: Darwin Family · ZTC Models — JEV ecosystems

🔁 RSI — a model that improves from its own work

Recursive self-improvement (RSI) is the core of this generation. Instead of distilling a bigger teacher, the model improves by learning from itself:

Solve — the model works through practice problems it has never seen in evaluation.
Verify — its answers are checked against verifiable references (answer keys, executable checks). Nothing unverified is learned.
Learn — it is re-trained on the reasoning that turned out to be correct.
Repeat — the improved model becomes the next solver.

What it bought in this release:

	Parent (Qwen3.8-Flash-Next)	Darwin-180B-RSI
Average reasoning length (MMLU-Pro)	4,320 tokens	3,833 tokens (−11 %)
MMLU-Pro accuracy	88.04 %	88.12 %

Same or better accuracy with shorter reasoning — cheaper and faster to serve. Practice sets are deduplicated against every evaluation set we report (8-gram overlap filter).

🏛️ ZTC — it knows before it answers

Zero-Token Confidence (ZTC) reads the model's own internal state once, before generation, and returns the probability that the answer it is about to give is correct — no extra tokens, no second model.

{"answer": "...", "confidence": 0.93, "ztc_score": 1.84, "truncated": false}

Use it to gate actions: when confidence is low, do not call the tool, escalate, or answer "I don't know".

What ships with this model

File	Role
`handler.py`	one call returns the answer and its confidence as JSON
`ztc/ztc_probe_darwin180rsi.npz`	the ZTC readout for this model (final layer, last prompt token)
`ztc/usage.py`	minimal example

from handler import EndpointHandler
h = EndpointHandler("FINAL-Bench/Darwin-180B-RSI")   # local snapshot path
print(h({"inputs": "What is 17 * 23?"}))
# [{"answer": "...391...", "confidence": 0.97, "ztc_score": 2.1, "truncated": false}]

Same format as Darwin-397B-ZTC. The readout is fitted only on practice data that is disjoint from every benchmark reported here.

🏆 Results

Benchmark	Score	Setting	Leaderboard
GPQA Diamond (198)	94.44	majority vote over up to 16 samples · 131,072-token thinking budget	#1
MMLU-Pro (12,032)	88.12	single sample · 131,072-token thinking budget	#1
AIME 2026 (30)	100.0	majority vote over 16 samples (mean accuracy 98.75) · 131,072-token thinking budget	#1
HMMT Feb 2026 (33)	100.0	majority vote over 16 samples (mean accuracy 96.59) · 131,072-token thinking budget	#1
MMMU-Pro (vision, 1,730)	79.48	majority vote over 3 samples · 131,072-token thinking budget	#1

Evaluation protocol

Common to every benchmark

Setting	Value
Thinking budget	131,072 tokens (max generated tokens per sample)
Sampling	temperature 1.0 · top_p 0.95 · top_k 20
Precision	bf16
Engine	vLLM, tensor parallel 8 (or 4), expert parallel

Per benchmark

Benchmark	Samples per question	Reported score
AIME 2026	16	majority vote (maj@16); mean over 16 = 98.75
HMMT Feb 2026	16	majority vote (maj@16); mean over 16 = 96.59
GPQA Diamond	up to 16	majority vote
MMLU-Pro	1	single sample (no voting)
MMMU-Pro (vision)	3	majority vote (maj@3)

All numbers are self-measured and reproducible with the settings above. Majority-vote scores are system scores (several samples per question) and are labeled as such.

MMLU-Pro by category (single sample) — strongest in math 95.0 · biology 94.6 · physics 92.5; room to grow in law and history.

⚙️ Specifications


Architecture	Mixture-of-Experts, hybrid attention (36 linear-attention + 12 full-attention layers)
Layers / hidden	48 / 2,560
Experts	512 routed (10 active per token) + shared expert
Context	262,144 tokens
Vocabulary	248,320
Modalities	image + text → text
Precision	bf16 (~336 GB)

🚀 Quickstart

Serving with vLLM (8 × B200 or equivalent)

vllm serve FINAL-Bench/Darwin-180B-RSI \
  --tensor-parallel-size 8 --enable-expert-parallel \
  --max-model-len 135168 --trust-remote-code

Chat Completions (OpenAI-compatible)

from openai import OpenAI
c = OpenAI(base_url="http://localhost:8000/v1", api_key="-")
r = c.chat.completions.create(model="FINAL-Bench/Darwin-180B-RSI",
    messages=[{"role": "user", "content": "Explain why the sky is blue in two sentences."}],
    temperature=1.0, top_p=0.95, extra_body={"top_k": 20})
print(r.choices[0].message.content)

Transformers

from transformers import AutoProcessor, AutoModelForImageTextToText
model_id = "FINAL-Bench/Darwin-180B-RSI"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

Tip: this is a thinking model. Give it room — a thinking budget of 32K–131K tokens is recommended for hard reasoning. Short budgets truncate the reasoning and cost accuracy.

⚠️ Limitations and disclosure

Scores are self-measured with the settings stated in the Results table; majority-vote numbers use several samples per question.
Very long reasoning is normal for hard problems; a short thinking budget will truncate answers and lower accuracy.
Like every LLM, the model can be confidently wrong — use the ZTC confidence readout to gate high-stakes actions.

🔗 Related Darwin Models

Darwin-397B-ZTC — 397B MoE (FP8), GPQA Diamond 93.43 %, ZTC on board
Darwin-28B-REASON — 28B, GPQA Diamond 89.39 %
Darwin-36B-Opus — 36B MoE, GPQA Diamond 88.4 %
Darwin-27B-RSI — 27B, the first Darwin RSI model
Darwin-9B-NEG — 9B with Negentropy distillation, GPQA Diamond 84.3 %
ZTC-Judge-27B — standalone ZTC judge

📚 Citation

@misc{darwin180b_rsi_2026,
  title  = {Darwin-180B-RSI: Recursive Self-Improvement on Verified Answers for a 180B Mixture-of-Experts Reasoning Model},
  author = {FINAL-Bench / Darwin Research Team},
  year   = {2026},
  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-180B-RSI}},
  note   = {GPQA Diamond 94.44 \% · MMLU-Pro 88.12 \%}
}

@misc{darwin_family_2026,
  title  = {Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning},
  author = {Kim, Taebong and Hong, Youngsik and Kim, Minsik and Choi, Sunyoung and Jang, Jaewon and Shin, Junghoon},
  year   = {2026},
  eprint = {2605.14386},
  archivePrefix = {arXiv}
}

@misc{latin_square_2026,
  title  = {Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks},
  author = {Kim, Taebong and Hong, Youngsik and Kim, Minsik and Choi, Sunyoung and Jang, Jaewon and Kim, Minseo},
  year   = {2026},
  eprint = {2609.20269},
  archivePrefix = {arXiv}
}

📜 License

Darwin-180B-RSI is a derivative of Qwen3.8-Flash-Next and is distributed under the Qwen Community License 1.0 (see LICENSE).

🏢 About

Built by VIDRAFT · evaluated with FINAL-Bench.

This model is part of the Darwin Family.

Downloads last month: 70

Safetensors

Model size

180B params

Tensor type

BF16

I64

Space using FINAL-Bench/Darwin-180B-RSI 1

Collections including FINAL-Bench/Darwin-180B-RSI

DARWIN-Family

Collection

비드래프트 • 54 items • Updated about 16 hours ago • 43

ZTC Models: JEV ecosystems

Collection

Answer verification from one forward pass, zero generated tokens. Measured against JEV and 10 others on 2,018 identical items. • 9 items • Updated about 14 hours ago • 39

Papers for FINAL-Bench/Darwin-180B-RSI

Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks

Paper • 2609.20269 • Published Jul 29 • 2

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

Paper • 2605.14386 • Published May 14 • 52

Evaluation results

Idavidrein/gpqa · Diamond View evaluation results leaderboard

94.44 ^*
TIGER-Lab/MMLU-Pro · Mmlu Pro View evaluation results leaderboard

88.12 ^*
MMMU/MMMU_Pro · Mmmu Pro Vision View evaluation results leaderboard

79.48 ^*
MathArena/aime_2026 · MathArena Aime 2026 View evaluation results leaderboard

100 ^*
MathArena/hmmt_feb_2026 · MathArena Hmmt Feb 2026 View evaluation results leaderboard

100 ^*

Accuracy (majority vote, up to 16 samples, 131K thinking) on GPQA Diamond
self-reported

94.440
Accuracy (single sample, 131K thinking) on MMLU-Pro
test set self-reported

88.120
Accuracy (majority vote, 3 samples, 131K thinking) on MMMU-Pro (vision)
test set self-reported

79.480