Leaderboard - FINAL Bench 'Metacognitive'
π
46
Metacognitive
Young Sik Hong
RICHARDYHONG
AI & ML interests
None yet
Recent Activity
liked a Space about 15 hours ago
FINAL-Bench/Leaderboard liked a Space about 15 hours ago
FINAL-Bench/security-scan liked a Space about 15 hours ago
Heartsync/Prompt-DumpOrganizations
None yet
liked 3
Spaces about 15 hours ago
reactedto SeaWolf-AI's post with π₯πβ€οΈ about 20 hours ago
Post
2039
𧬠Darwin-27B-Opus: 86.9% on GPQA Diamond β World #5, Zero Training
We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond β ranking #5 globally on the HuggingFace leaderboard β without a single gradient update.
How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios β no human tuning required.
The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B β with zero training, zero data, one GPU, ~2 hours.
We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father β autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning.
π Public release: 10 days β 300+ community derivatives, 120K+ downloads.
π Links:
Darwin-27B-Opus: FINAL-Bench/Darwin-27B-Opus
article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa
Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family
If foundation models are raw ore, Darwin is the forge. We are just getting started. π₯
We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond β ranking #5 globally on the HuggingFace leaderboard β without a single gradient update.
How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios β no human tuning required.
The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B β with zero training, zero data, one GPU, ~2 hours.
We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father β autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning.
π Public release: 10 days β 300+ community derivatives, 120K+ downloads.
π Links:
Darwin-27B-Opus: FINAL-Bench/Darwin-27B-Opus
article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa
Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family
If foundation models are raw ore, Darwin is the forge. We are just getting started. π₯
liked a
model about 20 hours ago
upvoted an article about 20 hours ago
Article
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
β’
8
liked a
Space 1 day ago
upvoted a collection 1 day ago
reactedto SeaWolf-AI's post with β€οΈπ₯ 3 days ago
Post
2889
Why This Matters β David Defeats Goliath
MODEL: FINAL-Bench/Darwin-4B-David
SPACE: FINAL-Bench/Darwin-4B-david
We're releasing Darwin-4B-David, the first second-generation model in the Darwin Opus family. By evolving an already-evolved model, it achieves 85.0% on GPQA Diamond β surpassing its 58.6% original ancestor and even gemma-4-31B (84.3%) β with just 4.5B parameters.
Second-Generation Evolution
Most merges start from a base model and produce a single offspring. Darwin-4B-David breaks this pattern. The Father (Darwin-4B-Opus) was already evolved from gemma-4-E4B-it with Claude Opus reasoning distillation β a Gen-1 model. The Mother (DavidAU's DECKARD-Expresso-Universe) brings Unsloth deep tuning across 5 in-house datasets with thinking mode by default. Crossbreeding these two produced the first Gen-2 Darwin model.
Darwin V6's Model MRI scanned both parents across all 42 layers, assigning independent optimal ratios per layer. The Mother's creativity and Korean language hotspot (Layer 22-25, weight 0.95) was maximally absorbed, while the Father's reasoning core (Layer 30-40, weight 0.48) was preserved. This is "Merge = Evolve" applied recursively β evolution of evolution.
Benchmarks
Darwin-4B-David scores 85.0% on GPQA Diamond (+26.4%p over original 58.6%), evaluated generatively with maj@8 (8 generations per question, majority vote), Epoch AI prompt format, thinking mode enabled, 50 sampled questions. On ARC-Challenge (25-shot, loglikelihood), both score 64.93% β expected, as loglikelihood doesn't capture thinking-mode reasoning differences.
Why This Matters
gemma-4-31B (30.7B) scores 84.3%. Darwin-4B-David surpasses it at 1/7th the size β no training, no RL, just 45 minutes of MRI-guided DARE-TIES on one H100. The name "David" honors Mother creator DavidAU and evokes David vs. Goliath.
MODEL: FINAL-Bench/Darwin-4B-David
SPACE: FINAL-Bench/Darwin-4B-david
We're releasing Darwin-4B-David, the first second-generation model in the Darwin Opus family. By evolving an already-evolved model, it achieves 85.0% on GPQA Diamond β surpassing its 58.6% original ancestor and even gemma-4-31B (84.3%) β with just 4.5B parameters.
Second-Generation Evolution
Most merges start from a base model and produce a single offspring. Darwin-4B-David breaks this pattern. The Father (Darwin-4B-Opus) was already evolved from gemma-4-E4B-it with Claude Opus reasoning distillation β a Gen-1 model. The Mother (DavidAU's DECKARD-Expresso-Universe) brings Unsloth deep tuning across 5 in-house datasets with thinking mode by default. Crossbreeding these two produced the first Gen-2 Darwin model.
Darwin V6's Model MRI scanned both parents across all 42 layers, assigning independent optimal ratios per layer. The Mother's creativity and Korean language hotspot (Layer 22-25, weight 0.95) was maximally absorbed, while the Father's reasoning core (Layer 30-40, weight 0.48) was preserved. This is "Merge = Evolve" applied recursively β evolution of evolution.
Benchmarks
Darwin-4B-David scores 85.0% on GPQA Diamond (+26.4%p over original 58.6%), evaluated generatively with maj@8 (8 generations per question, majority vote), Epoch AI prompt format, thinking mode enabled, 50 sampled questions. On ARC-Challenge (25-shot, loglikelihood), both score 64.93% β expected, as loglikelihood doesn't capture thinking-mode reasoning differences.
Why This Matters
gemma-4-31B (30.7B) scores 84.3%. Darwin-4B-David surpasses it at 1/7th the size β no training, no RL, just 45 minutes of MRI-guided DARE-TIES on one H100. The name "David" honors Mother creator DavidAU and evokes David vs. Goliath.
liked a
Space 3 days ago
liked a
model 3 days ago
liked a
model 4 days ago
upvoted an article 6 days ago
Article
Darwin V6: Diagnostic-Guided Evolutionary Model Merging
β’
11
liked a
Space 6 days ago
liked a
model 6 days ago
reactedto SeaWolf-AI's post with π₯ 6 days ago
Post
5517
𧬠Darwin V6: Diagnostic-Guided Evolutionary Model Merging
We are releasing Darwin-31B-Opus β a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.
Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus
π¬ What Darwin V6 Does
Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.
Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.
combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)
When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.
𧬠Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill
𧬠Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) β +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 β FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...
We are releasing Darwin-31B-Opus β a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.
Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus
π¬ What Darwin V6 Does
Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.
Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.
combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)
When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.
𧬠Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill
𧬠Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) β +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 β FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...
- 11 replies
liked a
Space 6 days ago