Darwin-28B-Opus

Abstract

Darwin-28B-Opus is the first reasoning model of the Darwin series built on the Qwen3.6 generation backbone. Produced by the Darwin V7 evolutionary breeding engine from two publicly available parents, it combines the strong bilingual reasoning of Qwen3.6-27B with Claude Opus 4-style chain-of-thought distilled behaviour.

On the GPQA Diamond graduate-level reasoning benchmark (198 PhD-level questions), Darwin-28B-Opus scores 88.89 % under the standard 3-stage adaptive evaluation, slightly edging out its larger MoE sibling Darwin-36B-Opus (88.4 %) and clearly surpassing its Qwen3.5-generation counterpart Darwin-27B-Opus (86.9 %).

---

🧬 Model Lineage

Why 28B? The 28B label denotes the Qwen3.6-generation member of the Darwin lineup (+1 over the Qwen3.5-era Darwin-27B-Opus). The actual parameter count is 27.6 B, and the architecture exactly follows Qwen3.6-27B.

---

⚙️ Technical Specifications

---

🏆 Benchmark — GPQA Diamond (198 questions)

Darwin-28B-Opus is evaluated under our standard 3-stage adaptive evaluation protocol, identical to the protocol used across the Darwin series.

Key performance indicators:

• Stage 1 → Stage 3: +14.14 %p through adaptive protocol
• vs Darwin-27B-Opus (86.9 %): +1.99 %p
• vs Darwin-36B-Opus (88.4 %): +0.49 %p
• vs Darwin-31B-Opus (85.9 %): +2.99 %p

---

🚀 Usage

Standard inference (Stage 1 baseline)

python
Copy code
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tok = AutoTokenizer.from_pretrained(
    "FINAL-Bench/Darwin-28B-Opus",
    trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
    "FINAL-Bench/Darwin-28B-Opus",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "user",
     "content": "Solve: If f(x) = x³ − 3x + 2, find all critical points and classify them."}
]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=False)
print(tok.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

Enhanced accuracy (Stage 2-3 adaptive)

For leaderboard-grade accuracy, combine:

1. Stage 1 greedy baseline,
2. Stage 2 maj@8 temperature sampling on low-confidence answers,
3. Stage 3 adaptive refinement on still-disputed answers.

Reference implementation is provided in the Darwin-series evaluation harness.

---

🎯 Recommended Use-Cases

• Graduate-level STEM reasoning (GPQA / science qualifying exams)
• Mathematical problem solving (MATH, AIME-style problems)
• Code generation and debugging (HumanEval, MBPP)
• Complex multi-step chain-of-thought tasks
• Bilingual reasoning (strong English + Korean; also Chinese / Japanese)

⚠️ Limitations

• At 27.6 B parameters in bfloat16, full inference requires ≈ 55 GB of VRAM (e.g., a single A100-80GB or B200).
• Optimised for English first, with secondary support for Korean, Chinese, and Japanese.
• Deep Opus-style reasoning traces tend to be verbose — control with max_new_tokens as needed.

---

📚 Citation

bibtex
Copy code
@misc{darwin28b_opus_2026,
  title  = {Darwin-28B-Opus: Evolutionary Merging of Qwen3.6-27B with Claude-Opus-Distilled Reasoning},
  author = {FINAL-Bench / Darwin Research Team},
  year   = {2026},
  howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-28B-Opus}},
  note   = {Darwin V7 · Mother-centric Ratio Interpolation merge · 88.89 % GPQA Diamond (3-stage)}
}

---

🔗 Related Darwin Models

• Darwin-36B-Opus — MoE 36B, Qwen3.6-35B-A3B × Opus distilled, GPQA 88.4 %
• Darwin-31B-Opus — 31B dense, multilingual-strong reasoning, GPQA 85.9 %
• Darwin-27B-Opus — 27B dense (Qwen3.5 generation), GPQA 86.9 %
• Darwin-9B-NEG — 9B with Native Entropy Gating, GPQA 84.3 %
• Darwin-9B-Opus — the Qwen3.5-9B Darwin member
• Darwin-4B-Genesis — smallest Darwin member

---

This model is introduced in Darwin Family.

Darwin V7 · Qwen3.6 generation flagship · Sealed 2026-04-25 · FINAL-Bench