Darwin-28B-Opus — Qwen3.6-27B × Opus-Distilled Evolutionary Merge

Qwen3.6-27B dense · 27.6B parameters · Hybrid Linear/Full Attention · BF16 · Thinking Mode · Apache 2.0 Darwin V7 evolutionary merge: Father × Opus-distilled Mother → 88.89% on GPQA Diamond (3-stage adaptive evaluation)

---

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

Role	Model	Role in the Merge
Father (父)	Qwen/Qwen3.6-27B	Qwen3.6 generation dense backbone with hybrid linear/full attention.
Mother (母)	rico03/Qwen3.6-27B-Claude-Opus-Reasoning-Distilled	Claude Opus reasoning-distilled variant of the same backbone (Jackrong-style distillation, 14 k traces).
Offspring	Darwin-28B-Opus (this model)	Darwin V7 evolutionary merge; Qwen3.6 architecture retained, Opus reasoning style inherited.

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

Component	Value
Architecture	Qwen3_5ForConditionalGeneration (Qwen3.6 generation, hybrid linear + full attention)
Parameters	27.6 B (BF16)
Hidden size	5 120
Intermediate size	17 408
Head dim	256
Layers	64 (3 linear : 1 full attention, full_attention_interval = 4)
Precision	bfloat16
Context length	Inherited from base (long-chain reasoning supported)
License	Apache 2.0

---

🏆 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.

Stage	Decoding Protocol	Cost	Accuracy
Stage 1	Single-shot greedy baseline	1×	74.75 % (148 / 198)
Stage 2	Majority vote ×8 at temperature 0.7 on Stage-1 wrongs	8×	83.84 % (166 / 198)
Stage 3	Adaptive ensemble refinement (close-tie tiebreaker + iterative MTI on residual hard questions)	≈ 20×	🥇 88.89 % (176 / 198)

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)

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

@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

---

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