The Father (Qwen3.5-35B-A3B) excels in versatility but scores 84.2% on hard reasoning. Darwin pushes reasoning to 90.0% while maintaining Father-level multilingual knowledge (MMMLU 85.0% vs 85.2%) and all general capabilities.
Conclusion: The only model that surpasses the Mother's reasoning, preserves the Father's multilingual knowledge, and retains full multimodal capabilities.
Model Overview
Darwin-35B-A3B-Opus is a next-generation reasoning-enhanced language model created by VIDRAFT's Darwin V5 evolution engine.
Claude 4.6 Opus CoT distillation, structured step-by-step reasoning, coding agent compatibility
Darwin V5 — Beyond Simple Merge
Limitations of Conventional Merging
Traditional model merging relies on humans setting hyperparameters like ratio and density by intuition. Set ratio=0.5, density=0.9, run once, and hope for the best. The result depends on luck, and applying the same ratio uniformly across billions of parameters ignores each layer's unique role.
Darwin V4's Advance
Darwin V4 solved this with evolutionary algorithms — automatically searching hundreds of parameter combinations and selecting survivors by real benchmark scores. But V4 was still blind evolution: it didn't know what each layer does.
Darwin V5: Model MRI Opens the Eyes
V5 integrates Model MRI (neural anatomy analyzer) to give evolution "sight":
[Phase 0] Model MRI — CT-scan both parents layer by layer
↓ "Father's layers 15-25 concentrate multilingual knowledge"
↓ "Mother's layers 30-40 concentrate reasoning patterns"
↓
[Phase 1] MRI-Guided Evolution — Start from scan-informed initial genome
↓ Not random, but "informed by CT results"
↓
[Phase 2] mergekit real merge + benchmark fitness selection
↓ Faster convergence in MRI-narrowed search space
↓
[Phase 3] MRI Health Check — CT-scan the child model
↓ Detect interference, function loss
↓ Prescribe layer-specific ratio adjustments
↓
[Final] Darwin-35B-A3B-Opus
V4 vs V5
Darwin V4
Darwin V5
Analogy
Mixing recipes blindfolded
Precision surgery with X-ray
Initial genome
Random
MRI-guided
Layer control
2 ratios (attn/ffn)
40 layers independently
Pre-diagnosis
❌ None
✅ Phase 0 MRI scan
Post-verification
Benchmark only
✅ Phase 3 health check
Search efficiency
Wide space
Narrowed, guided search
Failure diagnosis
Unknown "why"
Pinpoint which layer failed
Darwin V4: Discovered Optimal Parameters (Blind Evolution)
Parameter
Value
Meaning
ratio
0.481
Father 52% : Mother 48% asymmetric blend
density_a
0.855
Selected 85.5% of Father's weights
density_b
0.971
Adopted 97.1% of Mother's weights
attn
0.168
Only 16.8% change in attention layers
ffn
0.841
84.1% change in FFN layers
Interpretation: Attention patterns (what to focus on) are almost entirely preserved from the Father, while FFN layers (knowledge storage) are largely replaced with the Mother's reasoning patterns.
Discovering attn=0.168 and ffn=0.841 — this extreme asymmetry — is virtually impossible by human intuition.
Darwin V5: MRI-Guided Merge Recipe
After scanning both parents, Model MRI generated a fundamentally different prescription:
MRI-Guided Genome
Parameter
V4 (Blind)
V5 (MRI)
Change
global_ratio
0.481
0.800
Mother weight ↑↑
attn_ratio
0.168
0.320
Attention also shifts to Mother
ffn_ratio
0.841
0.590
FFN becomes more conservative
density_a
0.855
0.799
Similar
density_b
0.971
0.799
Mother density ↓ (Dead Expert compensation)
Key insight: MRI prescribed "use more of the Mother (ratio 0.8), but reduce density (0.799) because 50-65% of her experts are dead." V4 found ratio=0.481 blindly — the opposite direction.
Layer-Wise Merge Strategy (3 Blocks)
MRI didn't apply uniform ratios. It split 40 layers into 3 blocks:
Merge Ratio + Parent Importance + MoE Health per Layer
L38 is the "Golden Layer": Mother's MRI showed peak cosine distance at L34~L38 (see Mother MRI below). Darwin V5 responded by assigning t=0.9 to L38 — transplanting the Mother's reasoning engine almost entirely.
Model MRI Scans — Parent Neural Anatomy
Mother MRI: Claude 4.6 Opus Distilled
Mother Probe Cosine Distance
Probe-wise Layer Importance: L34~L38 shows intense red (high cosine distance) across REASONING, CODE, LOGIC probes — this is the Mother's reasoning engine.
Mother MoE Health
Metric
Status
Interpretation
Router Entropy
✅ ~1.0 across all layers
Healthy — experts evenly distributed
Dead Expert %
🔴 50~65%
Critical — Claude distillation killed half the experts
Expert Similarity
✅ 0.001~0.008
Healthy — surviving experts remain diverse
Dead Expert 50~65% is the fingerprint of Claude text-only distillation. The fine-tuning killed multimodal and multilingual experts that were no longer activated during text-only training.
Mother Expert Utilization
Expert Utilization Heatmap: Mostly dark (inactive) with sparse bright activations — the Claude reasoning pattern is concentrated in a small number of specialized experts.
Father MRI: Healthy Generalist (Organ Donor)
Father MoE Health
Father Expert Utilization
Father Layer Importance by Probe
The Father (Qwen3.5-35B-A3B) shows healthy, uniform expert activation across all 40 layers — a well-balanced generalist with all experts alive. This is the "organ donor" that revives the Mother's dead 50–65% experts.
Parent Comparison: Layer Advantage Map
Parent A vs B Layer Advantage
Above zero (↑ A): Father stronger — primarily L0~L5 (embedding/early layers)
Below zero (↓ B): Mother stronger — scattered but consistent across L5~L35
L34~L38: Mother shows strongest advantage in REASONING and CODE probes
L39: Father recovers — output layer favors Father's multimodal routing
This advantage map directly informed the 3-block merge recipe: Mother dominates L0~L38, Father retakes L39.
How GPQA 90% Was Achieved
Mother L34~L38 reasoning engine (MRI red zone)
↓ t=0.9 — transplanted almost entirely
+
Father L39 output router (multimodal/multilingual expert activation)
↓ t=0.53 — Father's routing preserved
+
Dead Expert replacement → Father's living experts fill Mother's dead slots
↓
= GPQA 90.0% (surpassed both parents)
The Mother's "reasoning brain" was transplanted while her dead experts were replaced with the Father's living ones. Reasoning went up, versatility was preserved.
Evolution History
Phase 1 → Phase 2 evolution complete
Final real_score: 0.8405
Merge time: 181.6 seconds
Merge commit: 109838c2
Model MRI Health Check — Child vs Parents
Darwin Health Check — Child vs Parents
✅ Health: Healthy — No issues detected.
The chart above shows the layer-by-layer importance of the child (Darwin, green bars) compared to both parents (Father = blue dashed, Mother = red dashed). Key findings:
Layer 0 (Embedding): Child importance spikes to 0.42 — both parents show similar peaks (~0.35–0.50). The child successfully inherited the critical embedding layer from both parents without interference.
Layers 1–33 (Middle): Near-zero importance across all three models. This is normal — middle layers in MoE models process information incrementally, with no single layer being critical. The child tracks both parents perfectly, confirming no function loss in the bulk of the network.
Layers 34–39 (Reasoning Engine): Importance rises sharply. This is the region where Mother's MRI showed intense reasoning activity (cosine distance > 0.6). The child's green bars match or exceed both parents — proving that Mother's reasoning patterns were successfully transplanted while Father's output routing was preserved.
Layer 39 (Output): Child peaks at ~0.48, closely matching both parents. The final output layer is intact.
Why This Matters
The MRI health check confirms three things:
No interference — No layer where child importance abnormally exceeds parents (which would indicate weight conflict)
No function loss — No layer where parents had high importance but child dropped to zero
Successful transplant — L34–L39 reasoning engine from Mother is fully operational in the child
MRI identified L34–L38 as Mother's reasoning core. Darwin assigned t=0.9 (90% Mother) to L38 specifically
Router Strategy: B→B→A
Mother's router for reasoning layers, Father's router for final output — preserves both reasoning paths and multimodal routing
Dead Expert Revival
Mother's 50–65% dead experts (killed by text-only fine-tuning) were replaced with Father's live experts — restoring multimodal and multilingual capabilities
Inherited Capabilities
From Father (Qwen3.5-35B-A3B)
Multimodal: Image and video understanding
201 Languages: Global linguistic coverage
262K Context: Native long-context (extendable to 1M via YaRN)
Structured Thinking: Systematic step-by-step reasoning within <think> tags
Efficient Reasoning: "Let me analyze this request carefully: 1..2..3..." pattern
Coding Agent Compatibility: Native "developer" role support for Claude Code, OpenCode
Tool Calling Stability: Consistent performance in tool-use scenarios
Autonomous Execution: Extended autonomous operation in agentic environments
Father's Official Benchmarks (Reference)
Darwin is built on this architecture with enhanced reasoning:
Category
Benchmark
Father Official
Knowledge
MMLU-Pro
85.3
Knowledge
MMLU-Redux
93.3
Reasoning
GPQA Diamond
84.2
Reasoning
HLE w/ CoT
22.4
Math
HMMT Feb 2025
89.0
Coding
SWE-bench Verified
69.2
Coding
LiveCodeBench v6
74.6
Agent
TAU2-Bench
81.2
Agent
BFCL-V4 (Tool Use)
67.3
Instruction
IFEval
91.9
Multilingual
MMMLU
85.2
Agentic Search
BrowseComp
61.0
Performance
Inference Speed
Metric
Value
Generation Speed
147.8 tok/s
Environment
Single NVIDIA H100 93GB NVL, SGLang, BF16
Qwen Official API
162.8 tok/s (Alibaba Cloud)
Hardware Requirements
Setup
VRAM
Status
BF16 (Full Precision)
65.5 GiB
Single H100 93GB NVL
93 GB
✅ Comfortable
Single A100 80GB
80 GB
⚠️ Tight
Single A100 40GB
40 GB
❌ Insufficient
Q8 Quantized
~35 GiB
Single A100 40GB
40 GB
✅ Possible
Q4_K_M Quantized
~18 GiB
Single RTX 4090 24GB
24 GB
✅ Comfortable
2× RTX 4090 (tp=2)
48 GB
✅ BF16 possible
As a Mixture-of-Experts model, only 3B parameters are active per token despite loading the full 35B. Quantization has minimal impact due to this sparsity.
What is Darwin-35B-A3B-Opus?
Darwin-35B-A3B-Opus is a 35 billion parameter Mixture-of-Experts language model (3B active per token) that was created using evolutionary merge techniques. It combines Qwen3.5-35B-A3B's multimodal versatility with Claude 4.6 Opus reasoning distillation, achieving 90.0% on GPQA Diamond — surpassing both parent models.
How does Darwin V5 differ from simple model merging?
Traditional merging applies uniform ratios by guesswork. Darwin V5 uses evolutionary algorithms (natural selection) combined with Model MRI (neural CT-scanning) to automatically discover optimal layer-specific merge ratios. For example, it found attn=0.168 and ffn=0.841 — an extreme asymmetry impossible to find by intuition.
What GPU do I need to run this model?
For BF16 full precision: A100 80GB (tight) or H100 93GB (comfortable). For Q4 quantization: a single RTX 4090 (24GB) is sufficient. The model loads 35B parameters but only activates 3B per token due to its MoE architecture.
Does it support multimodal (images/video)?
Yes. Darwin inherits the Father model's (Qwen3.5-35B-A3B) full multimodal capabilities including image and video understanding, unlike the Mother model which lost this during text-only fine-tuning.
What languages does it support?
201 languages and dialects, inherited from Qwen3.5's multilingual training. MMMLU benchmark confirms 85.0% multilingual knowledge retention across 29 evaluated languages.
What is Model MRI?
Model MRI is a neural anatomy analysis tool that CT-scans each layer of a language model to understand what functions it performs. When integrated with Darwin, it guides the evolutionary merge process — telling the algorithm which layers to preserve from each parent and which to replace. In this model, MRI identified L38 as the Mother's "golden layer" (core reasoning engine) and prescribed 90% Mother weight for that specific layer.
What are "Dead Experts" and why does it matter?
In Mixture-of-Experts (MoE) models, each layer contains hundreds of specialist sub-networks (experts). The Mother model's Claude distillation killed 50–65% of these experts because text-only fine-tuning didn't activate multimodal/multilingual specialists. Darwin's MRI detected this and prescribed replacing dead experts with the Father's living ones — reviving capabilities the Mother lost.
Is this model open source?
Yes. Darwin-35B-A3B-Opus is released under the Apache 2.0 license, fully open for commercial and research use.
