Instructions to use FINAL-Bench/Darwin-27B-RSI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-27B-RSI with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-27B-RSI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-27B-RSI")
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Darwin-27B-RSI", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Darwin-27B-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-27B-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-27B-RSI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-27B-RSI

SGLang

How to use FINAL-Bench/Darwin-27B-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-27B-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-27B-RSI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-27B-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-27B-RSI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-27B-RSI with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-27B-RSI
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Darwin-27B-RSI: A Model That Improved Itself — Zero Human Answers

Qwen3.5-27B family · 27B dense · Thinking mode · BF16 · Apache 2.0 No human-written answers. The model generated its own learning signal — and got measurably better.

Abstract

Darwin-27B-RSI is Darwin-27B-Opus after Recursive Self-Improvement (RSI): the model was improved using only signal it produced itself. No human-labeled answers were used at any stage.

Under an identical evaluation protocol, Darwin-27B-RSI improves over its parent on graduate-level science reasoning — +5.24 points on GPQA Diamond (single sample) and +3.79 points with majority voting — with every gain statistically significant in paired tests.

As the reasoning engine of Darwin-27B-JEV on the Decision Index, it lifts the hardest reasoning decisions: GPQA Diamond skill 0.31 → 0.71, GSM8K 0.61 → 0.97, MMLU-Pro 0.60 → 0.82.

What Is RSI?

Most models improve only when people write more answers for them. Recursive Self-Improvement removes that bottleneck: the model works on problems, judges its own work, and learns from what it produced — then repeats. Each improved model becomes the starting point for the next improvement.

Darwin-27B-RSI demonstrates this loop on a 27B model:

Human answers used: 0
Direction of change: measurably better on held-out graduate-level science
Contamination check: training problems share 0 items with the evaluation sets reported here

The training procedure itself is not released.

Results

Science reasoning (same protocol for both models)

Benchmark	Darwin-27B-Opus	Darwin-27B-RSI	Δ
GPQA Diamond (1 sample)	72.85	78.09	+5.24
GPQA Diamond (majority@16)	79.80	83.59	+3.79
SuperGPQA (1 sample)			+4.03

Both models were measured under the same protocol (single sample, identical sampling settings and token budget), so numbers differ from the Darwin-27B-Opus card, which reports a different protocol. All gains are statistically significant in paired tests.

Decision Index — as the reasoning engine of Darwin-27B-JEV

The Decision Index scores typed-decision engines on 43 benchmarks and ~121K decisions (chance-corrected: 0 = random, 1 = perfect). Darwin-27B-RSI handles the decisions that need real thinking:

Benchmark (skill)	before	with Darwin-27B-RSI
GPQA Diamond ★	0.31	0.71
GSM8K	0.61	0.97
CRUXEval	0.61	0.87
MMLU-Pro ★	0.60	0.82
BBH ★	0.68	0.83
CLadder	0.49	0.70

★ = gold benchmark (weighted 1.2× on the board). Darwin-27B-JEV: ≈ 61.1 under the v0.2.1 board rules (our recomputation; official score pending review). Full run: FINAL-Bench/Darwin-27B-JEV-decision-index.

Usage

Darwin-27B-RSI is a thinking model. Give it room to reason and read the answer after the reasoning block.

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "FINAL-Bench/Darwin-27B-RSI"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")

messages = [{"role": "user", "content": "A ball is thrown upward at 40 m/s. For how long is it above 40 m? (g = 10 m/s²) Think, then give the final answer."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=8192, temperature=0.6, top_p=0.95, do_sample=True)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))

vLLM

vllm serve FINAL-Bench/Darwin-27B-RSI --max-model-len 32768

Recommended: temperature 0.6, top_p 0.95, generous token budget (8K–16K) for hard problems.

Model Details


Parent	FINAL-Bench/Darwin-27B-Opus
Architecture	Qwen3.5 family, 27B dense
Precision	BF16
Improvement method	Recursive Self-Improvement, no human labels
License	Apache 2.0
Developer	VIDRAFT · FINAL-Bench

Limitations and Disclosure

Gains were measured on graduate-level science; other domains may change less.
As a thinking model, it can produce long reasoning; cap max_new_tokens for latency-sensitive use.
31 training problems (0.22% of the benchmark) overlap with the Decision Index MMLU set; no answer labels were used.
Not affiliated with TypeSafe AI or its Jev product.

Citation

@misc{darwin27b_rsi_2026,
  title  = {Darwin-27B-RSI: Recursive Self-Improvement without Human Labels},
  author = {VIDRAFT and FINAL-Bench},
  year   = {2026},
  url    = {https://huggingface.co/FINAL-Bench/Darwin-27B-RSI}
}

Downloads last month: -

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for FINAL-Bench/Darwin-27B-RSI

Base model

FINAL-Bench/Darwin-27B-Opus

Finetuned

(6)

this model

Quantizations

1 model