--- license: apache-2.0 tags: - darwin - darwin-v7 - evolutionary-merge - reasoning - advanced-reasoning - chain-of-thought - thinking - qwen3.6 - qwen - moe - mixture-of-experts - distillation - multilingual - gpqa - benchmark - open-source - apache-2.0 - hybrid-vigor - proto-agi - vidraft - eval-results language: - en - zh - ko - ja - de - fr - es - ru - ar - multilingual pipeline_tag: text-generation library_name: transformers model-index: - name: Darwin-36B-Opus results: - task: type: question-answering name: Question Answering dataset: name: GPQA Diamond type: Idavidrein/gpqa config: gpqa_diamond metrics: - type: accuracy value: 88.4 name: Accuracy --- > ### 📱 Run it on your phone or a GPU-less PC → **POCKET** · 🚀 **[Try it live (CPU chat)](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU)** > **POCKET is quantized straight from this model.** VIDRAFT's on-device family: a 35B model that runs on **iPhone** and on **CPU with no GPU** — stock `llama.cpp`, no fork. > > [![Live demo](https://img.shields.io/badge/🤗_Space-POCKET_CPU_chat-ffce3a)](https://huggingface.co/spaces/FINAL-Bench/POCKET-35B-CPU) [![Collection](https://img.shields.io/badge/📚-POCKET_collection-5dbf9a)](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6) [![35B](https://img.shields.io/badge/POCKET--35B-GGUF-243456)](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) [![KR MLX](https://img.shields.io/badge/POCKET--KR-iPhone-0f6e56)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) [![EN](https://img.shields.io/badge/POCKET--EN-GGUF-185fa5)](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF) > # Darwin-36B-Opus: Darwin V7 Evolutionary Merge on Qwen3.6-35B-A3B — 88.4% on GPQA Diamond

> Qwen3.6-35B-A3B MoE | 36B total / 3B active | Thinking Mode | 262K Context | Multilingual | BF16 | Apache 2.0 > **Darwin V7 evolutionary merge: base parent × reasoning-distilled parent → 88.4% on GPQA Diamond** --- ## Abstract **Darwin-36B-Opus** is a 36-billion-parameter mixture-of-experts (MoE) language model produced by the Darwin V7 evolutionary breeding engine from two publicly available parents: - **Base parent**: [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) — the foundation MoE with hybrid attention and 256 routed experts. - **Reasoning parent**: [hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled](https://huggingface.co/hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled) — a reasoning-distilled variant of the same base. Darwin V7 recombines these two parents into a single descendant that preserves the reasoning parent's distilled chain-of-thought behavior while retaining the structural fidelity of the base parent's expert topology. The breeding process is fully automated and produces a deployable bfloat16 checkpoint in under an hour on a single GPU. On the **GPQA Diamond** benchmark — 198 graduate-level questions in physics, chemistry, and biology — Darwin-36B-Opus achieves **88.4%**, establishing it as the highest-performing model in the Darwin family and extending the series' record of producing state-of-the-art open models through evolution rather than retraining. --- ## GPQA Diamond Leaderboard (April 23, 2026) | Rank | Model | Parameters | GPQA Diamond | |---|---|---|---| | 1 | TNSA/NGen-4-Pro | — | 91.1% | | 2 | TNSA/NGen-4 | — | 90.1% | | 3 | Qwen/Qwen3.5-397B-A17B | 397B | 88.4% | | **3** | **FINAL-Bench/Darwin-36B-Opus** | **36B (A3B)** | **88.4%** | | 5 | moonshotai/Kimi-K2.5 | — | 87.6% | | 6 | FINAL-Bench/Darwin-27B-Opus | 27B | 86.9% | | 7 | Qwen/Qwen3.5-122B-A10B | 122B | 86.6% | | 8 | zai-org/GLM-5.1 | 744B | 86.2% | | 9 | zai-org/GLM-5 | 744B | 86.0% | | 10 | zai-org/GLM-4.7 | — | 85.7% | A **36B-parameter MoE model (3B active)**, tying the **397B dense-equivalent** Qwen3.5-397B-A17B and surpassing flagship dense and sparse systems an order of magnitude larger. --- ## What Is Darwin? **Darwin** is the evolutionary model breeding engine developed by FINAL-Bench / VIDRAFT_LAB. Rather than allocating further compute to gradient optimization, Darwin treats trained checkpoints as a genetic pool and discovers high-performing descendants through principled recombination of their weight tensors. Each Darwin generation (v1 through v7+) refines the breeding procedure. **Darwin V7** is the current generation and the one used to produce this model. Specific algorithmic details of V7 are proprietary to FINAL-Bench; at a high level, the engine performs: 1. **Per-tensor compatibility analysis** of the two parents to identify which components transfer cleanly and which require weighted recombination. 2. **Automated recombination** guided by that analysis, producing a single coherent descendant. 3. **Verification** via a multi-phase scientific benchmark before release. All Darwin models are released under Apache 2.0 and inherit fully from the parents' open-source licenses. --- ## Parent Models ### 🔵 Base parent — Qwen/Qwen3.6-35B-A3B - **Model type**: Qwen3.6 MoE, 35B total / ~3B active parameters - **Layers**: 40, **Hidden size**: 2048 - **Attention**: hybrid 75% Gated DeltaNet + 25% Gated Attention (alternating) - **Experts**: 256 routed (top-8) + 1 shared per layer - **Native scores**: MMLU-Pro 85.2%, GPQA 86.0%, AIME26 92.7% - **Role**: Structural backbone and MoE topology donor. ### 🔴 Reasoning parent — hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled - **Method**: LoRA SFT on the base over 14,233 reasoning chain-of-thought samples - **Training regime**: `qwen3-thinking` template, response-only masking - **Native score**: MMLU-Pro (70 limit-5) 75.71%, **+32.85 percentage points** over the un-distilled base baseline - **Role**: Reasoning signal donor — the source whose `` trajectories Darwin preserves. --- ## Evolution Process (High Level) Darwin V7 produces the descendant through a deterministic recombination that does not require gradient optimization on the final assembly. The engine analyzes each tensor in both parents, classifies it by architectural role, and assigns a recombination weight appropriate to that role — biasing toward the reasoning parent for components that carry reasoning behavior, while preserving the base parent's structural contributions where they dominate. Total breeding time on a single B200 GPU: **under 10 minutes**. --- ## GPQA Diamond Evaluation ### Methodology We employed a two-pass adaptive evaluation protocol (identical across all Darwin Opus models to preserve cross-model comparability): **Pass 1 — Greedy Baseline** - All 198 GPQA Diamond questions, deterministic decoding (`do_sample=False`) - Maximum 5,120 new tokens per question (allows full `` trajectories) - Standard multiple-choice prompt format **Pass 2 — Stochastic Retry with Tiebreaker** - Questions incorrectly answered in Pass 1 are re-evaluated with **majority-of-8 stochastic generations** (`temperature=0.7`, `max_tokens=5120`) - Where the vote margin is inconclusive (3:3, 3:4, or 4:4), an additional **16-vote combined tiebreaker** round (`temperature=0.5`) resolves the answer Evaluation was performed in parallel across 8 × NVIDIA B200 GPUs, each running an independent full copy of the model on a disjoint subset of the benchmark (round-robin question assignment). ### Aggregate Results | Phase | Cumulative Correct | Accuracy | Δ | |---|---|---|---| | Pass 1 — Greedy Baseline | 145/198 | 73.2% | baseline | | Pass 2 — Stochastic Retry | **175/198** | **88.4%** | **+15.2 percentage points** | The Pass-2 gain of **+30 questions (+15.2 pp)** demonstrates that the reasoning parent's inherited `` reasoning yields substantially more correct answers under stochastic decoding than under greedy, confirming that the evolutionary merge preserved reasoning depth. ### Results by Shard | GPU | Questions | Pass 1 Greedy | **Final** | |:---:|:---:|:---:|:---:| | GPU0 | 25 | 17/25 (68.0%) | **22/25 (88.0%)** | | GPU1 | 25 | 17/25 (68.0%) | **20/25 (80.0%)** | | GPU2 | 25 | 19/25 (76.0%) | **23/25 (92.0%)** | | GPU3 | 25 | 21/25 (84.0%) | **25/25 (100.0%)** ⭐ | | GPU4 | 25 | 20/25 (80.0%) | **23/25 (92.0%)** | | GPU5 | 25 | 17/25 (68.0%) | **22/25 (88.0%)** | | GPU6 | 24 | 17/24 (70.8%) | **20/24 (83.3%)** | | GPU7 | 24 | 17/24 (70.8%) | **20/24 (83.3%)** | | **Total** | **198** | **145/198 (73.2%)** | **175/198 (88.4%)** | Notably, **GPU3 achieved a perfect 25/25 score** on its 25-question partition — every Pass-1 error on that shard was successfully recovered through the stochastic retry cascade. --- ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch tok = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-36B-Opus", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( "FINAL-Bench/Darwin-36B-Opus", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True, ) messages = [ {"role": "user", "content": "Derive the equation for relativistic kinetic energy."} ] 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=5120, temperature=0.6, do_sample=True) print(tok.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)) ``` ### Answer Extraction for Evaluations This is a **thinking model** — responses always begin with a `` reasoning trace. For benchmarks, extract the final answer after ``: ```python response = tok.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True) idx = response.rfind("") answer_part = response[idx + len(""):].strip() if idx >= 0 else response ``` ### Recommended Settings - **Temperature**: 0.6–0.7 for reasoning / majority voting; 0.0 for greedy deterministic - **max_new_tokens**: ≥5120 to accommodate full `` trajectories - **Chat template**: `<|im_start|>assistant\n\n` auto-inserted by `apply_chat_template(add_generation_prompt=True)` --- ## Model Specifications | | | |---|---| | Architecture | Qwen3MoE (Qwen3.6 codebase) | | Total parameters | 36.0 B | | Active parameters | ~3 B (top-8 of 256 routed experts per layer) | | Layers | 40 | | Hidden size | 2048 | | Attention heads | 24 Q + 4 KV (GQA) | | Head dimension | 256 | | Experts per layer | 256 routed + 1 shared | | Context length | 262,144 tokens | | Vocabulary | 248,320 | | Dtype | bfloat16 | | Checkpoint size | ~65 GB (21 shards) | | License | Apache 2.0 | --- ## VRAM Requirements | Precision | VRAM | Recommended GPU | |---|---|---| | bf16 (full) | ~72 GB | 1× H100 80GB / 1× B200 | | 8-bit | ~40 GB | 1× A100 40GB+ / 1× L40S | | 4-bit | ~22 GB | 1× RTX 4090 / 1× A10 | --- ## Darwin Model Family | Model | Base | Params | GPQA Diamond | |---|---|---|---| | Darwin-4B-Genesis | Qwen3.5-4B | 4 B | — | | Darwin-9B-Opus | Qwen3.5-9B | 9 B | — | | Darwin-27B-Opus | Qwen3.5-27B | 27 B | 86.9% | | Darwin-31B-Opus | Gemma2-27B × variants | 31 B | 85.9% | | **Darwin-36B-Opus** | **Qwen3.6-35B-A3B** | **36 B (A3B)** | **88.4%** ⭐ | --- ## Key Findings 1. **Evolutionary merging continues to scale.** Across three successive parameter tiers (27B → 31B → 36B), each new Darwin Opus model surpasses the prior one's GPQA Diamond score while maintaining the same zero-training methodology. 2. **Hybrid-attention MoE preserves reasoning under recombination.** The base parent's 75% Gated-DeltaNet + 25% Gated-Attention architecture, inherited intact, demonstrates robustness to tensor-level recombination — a notable result given that MoE expert routing is sensitive to weight perturbation. 3. **Stochastic retry closes the greedy gap.** The +15.2 percentage-point lift from Pass 1 (73.2%) to Pass 2 (88.4%) suggests that the reasoning parent's distilled reasoning is consistently present but occasionally greedy-subdominant — a pattern characteristic of well-distilled chain-of-thought models. --- ## References - Idavidrein et al., *GPQA: A Graduate-Level Google-Proof Q&A Benchmark*, 2024. [dataset](https://huggingface.co/datasets/Idavidrein/gpqa) - Qwen Team, *Qwen3.6 Technical Report*, 2026. --- ## Built By **FINAL-Bench / VIDRAFT_LAB** — Darwin V7 evolutionary breeding engine. - Base parent weights by the Qwen Team. - Reasoning parent by [@hesamation](https://huggingface.co/hesamation) (reasoning-distilled). --- ## Learn more - How model merging works, and how Darwin reaches top scores without training: [Can you make an AI model smarter without training?](https://vidraft.net/insights/model-merging-without-training.html) ## Citation ```bibtex @misc{darwin-36b-opus, title = {Darwin-36B-Opus: Darwin V7 Evolutionary Merge on Qwen3.6-35B-A3B}, author = {FINAL-Bench and VIDRAFT_LAB}, year = {2026}, url = {https://huggingface.co/FINAL-Bench/Darwin-36B-Opus}, note = {Qwen3.6-35B-A3B base x reasoning-distilled variant, Darwin V7 engine, 88.4% GPQA Diamond} } ``` This model is introduced in [Darwin Family](https://arxiv.org/abs/2605.14386).