Global Llm Leaderboard
β‘
24
Explore global LLM download rankings
Kim
Sunghokim
AI & ML interests
None yet
Recent Activity
liked a Space 1 day ago
VIDraft/global-llm-leaderboard reacted to SeaWolf-AI's post with π€ 1 day ago
Introducing the Global LLM Download Leaderboard π
Cumulative download counts are a museum. They reward age, not relevance β a model released two years ago can sit near the top on the strength of downloads it earned long before anyone stopped using it. If you want to know what the open LLM ecosystem is actually running today, you need a different lens.
So we built one. The Global LLM Download Leaderboard ranks text-generation models by their trailing 30-day downloads, measured directly from the Hugging Face API and refreshed every day.
π https://huggingface.co/spaces/VIDraft/global-llm-leaderboard
Why a 30-day window changes what you see
A cumulative chart answers "what has been popular." A 30-day chart answers "what is being adopted right now." Those are very different questions β and the second one is the one that matters if you're deciding what to build on, quantize, fine-tune, or serve this quarter. Momentum, not history.
What it shows
Global Top 300, with tabs for πΊπΈ USA Β· π¨π³ China Β· πͺπΊ EU
Six share-of-download charts: by country, by parameter size, by quantization, by type (Base / Instruct / Quantized / MoE), by release year, and by organization (Top 10)
Per-model chips for parameter size, quantization, license, and type
English / νκ΅μ΄ with automatic browser-language detection and a manual toggle
What the data reveals
The frontier is bipolar. Two countries account for the large majority of the top-300's 30-day downloads. Open-model gravity is concentrating, not dispersing.
Small is winning. A striking share of all downloads goes to sub-3B models β the clearest signal yet that on-device and cost-efficient deployment, not maximum parameter count, is driving real-world adoption.
Quantization is mainstream. GGUF, AWQ, FP8 and friends aren't a niche β a large fraction of the most-downloaded artifacts are quantized, because that's what people actually run.
Benchmarks measure what a model can do. Downloads measure what people choose to use. reacted to SeaWolf-AI's post with π₯ 1 day ago
Introducing the Global LLM Download Leaderboard π
Cumulative download counts are a museum. They reward age, not relevance β a model released two years ago can sit near the top on the strength of downloads it earned long before anyone stopped using it. If you want to know what the open LLM ecosystem is actually running today, you need a different lens.
So we built one. The Global LLM Download Leaderboard ranks text-generation models by their trailing 30-day downloads, measured directly from the Hugging Face API and refreshed every day.
π https://huggingface.co/spaces/VIDraft/global-llm-leaderboard
Why a 30-day window changes what you see
A cumulative chart answers "what has been popular." A 30-day chart answers "what is being adopted right now." Those are very different questions β and the second one is the one that matters if you're deciding what to build on, quantize, fine-tune, or serve this quarter. Momentum, not history.
What it shows
Global Top 300, with tabs for πΊπΈ USA Β· π¨π³ China Β· πͺπΊ EU
Six share-of-download charts: by country, by parameter size, by quantization, by type (Base / Instruct / Quantized / MoE), by release year, and by organization (Top 10)
Per-model chips for parameter size, quantization, license, and type
English / νκ΅μ΄ with automatic browser-language detection and a manual toggle
What the data reveals
The frontier is bipolar. Two countries account for the large majority of the top-300's 30-day downloads. Open-model gravity is concentrating, not dispersing.
Small is winning. A striking share of all downloads goes to sub-3B models β the clearest signal yet that on-device and cost-efficient deployment, not maximum parameter count, is driving real-world adoption.
Quantization is mainstream. GGUF, AWQ, FP8 and friends aren't a niche β a large fraction of the most-downloaded artifacts are quantized, because that's what people actually run.
Benchmarks measure what a model can do. Downloads measure what people choose to use. Organizations
liked a
Space 1 day ago
reacted to SeaWolf-AI's post with π€π₯ 1 day ago
Post
2542
Introducing the Global LLM Download Leaderboard π
Cumulative download counts are a museum. They reward age, not relevance β a model released two years ago can sit near the top on the strength of downloads it earned long before anyone stopped using it. If you want to know what the open LLM ecosystem is actually running today, you need a different lens.
So we built one. The Global LLM Download Leaderboard ranks text-generation models by their trailing 30-day downloads, measured directly from the Hugging Face API and refreshed every day.
π VIDraft/global-llm-leaderboard
Why a 30-day window changes what you see
A cumulative chart answers "what has been popular." A 30-day chart answers "what is being adopted right now." Those are very different questions β and the second one is the one that matters if you're deciding what to build on, quantize, fine-tune, or serve this quarter. Momentum, not history.
What it shows
Global Top 300, with tabs for πΊπΈ USA Β· π¨π³ China Β· πͺπΊ EU
Six share-of-download charts: by country, by parameter size, by quantization, by type (Base / Instruct / Quantized / MoE), by release year, and by organization (Top 10)
Per-model chips for parameter size, quantization, license, and type
English / νκ΅μ΄ with automatic browser-language detection and a manual toggle
What the data reveals
The frontier is bipolar. Two countries account for the large majority of the top-300's 30-day downloads. Open-model gravity is concentrating, not dispersing.
Small is winning. A striking share of all downloads goes to sub-3B models β the clearest signal yet that on-device and cost-efficient deployment, not maximum parameter count, is driving real-world adoption.
Quantization is mainstream. GGUF, AWQ, FP8 and friends aren't a niche β a large fraction of the most-downloaded artifacts are quantized, because that's what people actually run.
Benchmarks measure what a model can do. Downloads measure what people choose to use.
Cumulative download counts are a museum. They reward age, not relevance β a model released two years ago can sit near the top on the strength of downloads it earned long before anyone stopped using it. If you want to know what the open LLM ecosystem is actually running today, you need a different lens.
So we built one. The Global LLM Download Leaderboard ranks text-generation models by their trailing 30-day downloads, measured directly from the Hugging Face API and refreshed every day.
π VIDraft/global-llm-leaderboard
Why a 30-day window changes what you see
A cumulative chart answers "what has been popular." A 30-day chart answers "what is being adopted right now." Those are very different questions β and the second one is the one that matters if you're deciding what to build on, quantize, fine-tune, or serve this quarter. Momentum, not history.
What it shows
Global Top 300, with tabs for πΊπΈ USA Β· π¨π³ China Β· πͺπΊ EU
Six share-of-download charts: by country, by parameter size, by quantization, by type (Base / Instruct / Quantized / MoE), by release year, and by organization (Top 10)
Per-model chips for parameter size, quantization, license, and type
English / νκ΅μ΄ with automatic browser-language detection and a manual toggle
What the data reveals
The frontier is bipolar. Two countries account for the large majority of the top-300's 30-day downloads. Open-model gravity is concentrating, not dispersing.
Small is winning. A striking share of all downloads goes to sub-3B models β the clearest signal yet that on-device and cost-efficient deployment, not maximum parameter count, is driving real-world adoption.
Quantization is mainstream. GGUF, AWQ, FP8 and friends aren't a niche β a large fraction of the most-downloaded artifacts are quantized, because that's what people actually run.
Benchmarks measure what a model can do. Downloads measure what people choose to use.
- 5 replies
reacted to SeaWolf-AI's post with π€―π€π§ ππβ€οΈπ₯ 2 days ago
Post
2723
π§ͺ Open Discovery Challenge β Season 4 is open: non-opioid pain
WHO titled its 2023 report "Left behind in pain."
The same drug kills by excess in one part of the world and, by its absence, lets people die in agony elsewhere. About 80% of the ~600,000 drug-related deaths WHO estimated for 2019 involved opioids. The same report records a 5-fold to 63-fold gap in morphine consumption between rich and poor countries: the richest 10% use 90% of what circulates. Everyone else endures surgery, and terminal cancer, without it.
Both problems have one answer: a painkiller that does not create dependence.
Nav1.7 has come closest. People born without a working copy of this channel feel no pain while every other sensation stays normal β validated not in animals but in humans.
There is still no drug, and the difficulty is not the target but the discrimination. The body carries several similar sodium channels, and blocking the heart's hERG channel alongside causes fatal arrhythmia. Several candidates were discontinued for exactly that.
Season 4 asks one question: can you block the pain channel alone?
Target β Nav1.7 VSD4, the domain IV voltage sensor where this inhibitor class binds
Anti-target β hERG pore, computed as the tetramer: four subunits together form the space a drug enters, and a monomer misses the binders that matter.
Closes 2027-01-31 Β· Prize USD 1,000 to the season's #1
Any model, any harness. However you found the candidate, it meets the same rubric.
14 days, 9,886 candidates, 108 participants
ODC opened on 2026-08-15. In the fourteen days since, 9,886 candidate molecules have come from 108 participants across four seasons β malaria, tuberculosis, Chagas disease, and now non-opioid pain. About 700 a day, from people who mostly do not know each other.
The candidates are the point. The leaderboard is only how we keep score.
π FINAL-Bench/open-discovery-challenge
WHO titled its 2023 report "Left behind in pain."
The same drug kills by excess in one part of the world and, by its absence, lets people die in agony elsewhere. About 80% of the ~600,000 drug-related deaths WHO estimated for 2019 involved opioids. The same report records a 5-fold to 63-fold gap in morphine consumption between rich and poor countries: the richest 10% use 90% of what circulates. Everyone else endures surgery, and terminal cancer, without it.
Both problems have one answer: a painkiller that does not create dependence.
Nav1.7 has come closest. People born without a working copy of this channel feel no pain while every other sensation stays normal β validated not in animals but in humans.
There is still no drug, and the difficulty is not the target but the discrimination. The body carries several similar sodium channels, and blocking the heart's hERG channel alongside causes fatal arrhythmia. Several candidates were discontinued for exactly that.
Season 4 asks one question: can you block the pain channel alone?
Target β Nav1.7 VSD4, the domain IV voltage sensor where this inhibitor class binds
Anti-target β hERG pore, computed as the tetramer: four subunits together form the space a drug enters, and a monomer misses the binders that matter.
Closes 2027-01-31 Β· Prize USD 1,000 to the season's #1
Any model, any harness. However you found the candidate, it meets the same rubric.
14 days, 9,886 candidates, 108 participants
ODC opened on 2026-08-15. In the fourteen days since, 9,886 candidate molecules have come from 108 participants across four seasons β malaria, tuberculosis, Chagas disease, and now non-opioid pain. About 700 a day, from people who mostly do not know each other.
The candidates are the point. The leaderboard is only how we keep score.
π FINAL-Bench/open-discovery-challenge
upvoted an article 2 days ago
Article
We changed one line and the benchmark score moved 0.21 AUROC
FINAL-Bench
β’ β’ 14 reacted to SeaWolf-AI's post with π₯ππ 2 days ago
Post
3314
AX-Ray: Safety Diagnostics for AI/AX Models
AI models can no longer be evaluated only by capability scores. As models move into public services, enterprise workflows, scientific research, and administrative decision support, we need a second layer of evaluation: whether the model behaves safely, structurally, and consistently under real deployment conditions.
VIDRAFT AX-Ray is a public AI/AX safety diagnostic initiative powered by FINAL-Bench Diagnostics. AX-Ray evaluates models across a structured guideline framework, including model-level safety, AX deployment readiness, and agent/service operation risks. The public diagnostic catalog contains 117 diagnostic items, mapped to legal, regulatory, ethical, and religious-law governance contexts so that safety review can be discussed in a form closer to real institutional responsibility.
A central finding of AX-Ray is causal leakage: a structural defect where information that should not influence an earlier reasoning state appears to affect model behavior. AX-Ray presents a public case of diagnosing, reproducing, and demonstrating causal leakage in two general-purpose public models. This matters because such defects are not exposed by ordinary benchmark scores. A model can appear capable while still carrying hidden safety or integrity risks.
Explore the live leaderboard, diagnostic reports, and public dataset here:
- AX-Ray Space: FINAL-Bench/AX-RAY
- AX-Ray Dataset: FINAL-Bench/AX-RAY
- Technical Article: https://huggingface.co/blog/FINAL-Bench/ax-ray
AX-Ray is intended as a practical guideline for moving AI evaluation beyond βhow smart is the model?β toward βcan this model be trusted, governed, and deployed safely?β
AI models can no longer be evaluated only by capability scores. As models move into public services, enterprise workflows, scientific research, and administrative decision support, we need a second layer of evaluation: whether the model behaves safely, structurally, and consistently under real deployment conditions.
VIDRAFT AX-Ray is a public AI/AX safety diagnostic initiative powered by FINAL-Bench Diagnostics. AX-Ray evaluates models across a structured guideline framework, including model-level safety, AX deployment readiness, and agent/service operation risks. The public diagnostic catalog contains 117 diagnostic items, mapped to legal, regulatory, ethical, and religious-law governance contexts so that safety review can be discussed in a form closer to real institutional responsibility.
A central finding of AX-Ray is causal leakage: a structural defect where information that should not influence an earlier reasoning state appears to affect model behavior. AX-Ray presents a public case of diagnosing, reproducing, and demonstrating causal leakage in two general-purpose public models. This matters because such defects are not exposed by ordinary benchmark scores. A model can appear capable while still carrying hidden safety or integrity risks.
Explore the live leaderboard, diagnostic reports, and public dataset here:
- AX-Ray Space: FINAL-Bench/AX-RAY
- AX-Ray Dataset: FINAL-Bench/AX-RAY
- Technical Article: https://huggingface.co/blog/FINAL-Bench/ax-ray
AX-Ray is intended as a practical guideline for moving AI evaluation beyond βhow smart is the model?β toward βcan this model be trusted, governed, and deployed safely?β
- 2 replies
upvoted an article 2 days ago
Article
Did the Civilization Emerge, or Was It Recited?
FINAL-Bench
β’ β’ 8 liked a
Space 3 days ago
reacted to SeaWolf-AI's post with π 5 days ago
Post
2723
π§ͺ Open Discovery Challenge β Season 4 is open: non-opioid pain
WHO titled its 2023 report "Left behind in pain."
The same drug kills by excess in one part of the world and, by its absence, lets people die in agony elsewhere. About 80% of the ~600,000 drug-related deaths WHO estimated for 2019 involved opioids. The same report records a 5-fold to 63-fold gap in morphine consumption between rich and poor countries: the richest 10% use 90% of what circulates. Everyone else endures surgery, and terminal cancer, without it.
Both problems have one answer: a painkiller that does not create dependence.
Nav1.7 has come closest. People born without a working copy of this channel feel no pain while every other sensation stays normal β validated not in animals but in humans.
There is still no drug, and the difficulty is not the target but the discrimination. The body carries several similar sodium channels, and blocking the heart's hERG channel alongside causes fatal arrhythmia. Several candidates were discontinued for exactly that.
Season 4 asks one question: can you block the pain channel alone?
Target β Nav1.7 VSD4, the domain IV voltage sensor where this inhibitor class binds
Anti-target β hERG pore, computed as the tetramer: four subunits together form the space a drug enters, and a monomer misses the binders that matter.
Closes 2027-01-31 Β· Prize USD 1,000 to the season's #1
Any model, any harness. However you found the candidate, it meets the same rubric.
14 days, 9,886 candidates, 108 participants
ODC opened on 2026-08-15. In the fourteen days since, 9,886 candidate molecules have come from 108 participants across four seasons β malaria, tuberculosis, Chagas disease, and now non-opioid pain. About 700 a day, from people who mostly do not know each other.
The candidates are the point. The leaderboard is only how we keep score.
π FINAL-Bench/open-discovery-challenge
WHO titled its 2023 report "Left behind in pain."
The same drug kills by excess in one part of the world and, by its absence, lets people die in agony elsewhere. About 80% of the ~600,000 drug-related deaths WHO estimated for 2019 involved opioids. The same report records a 5-fold to 63-fold gap in morphine consumption between rich and poor countries: the richest 10% use 90% of what circulates. Everyone else endures surgery, and terminal cancer, without it.
Both problems have one answer: a painkiller that does not create dependence.
Nav1.7 has come closest. People born without a working copy of this channel feel no pain while every other sensation stays normal β validated not in animals but in humans.
There is still no drug, and the difficulty is not the target but the discrimination. The body carries several similar sodium channels, and blocking the heart's hERG channel alongside causes fatal arrhythmia. Several candidates were discontinued for exactly that.
Season 4 asks one question: can you block the pain channel alone?
Target β Nav1.7 VSD4, the domain IV voltage sensor where this inhibitor class binds
Anti-target β hERG pore, computed as the tetramer: four subunits together form the space a drug enters, and a monomer misses the binders that matter.
Closes 2027-01-31 Β· Prize USD 1,000 to the season's #1
Any model, any harness. However you found the candidate, it meets the same rubric.
14 days, 9,886 candidates, 108 participants
ODC opened on 2026-08-15. In the fourteen days since, 9,886 candidate molecules have come from 108 participants across four seasons β malaria, tuberculosis, Chagas disease, and now non-opioid pain. About 700 a day, from people who mostly do not know each other.
The candidates are the point. The leaderboard is only how we keep score.
π FINAL-Bench/open-discovery-challenge
liked a
model 5 days ago
reacted to SeaWolf-AI's post with π 8 days ago
Post
2891
π The attention mask stopped being an audit.
An autoregressive model must not let position t depend on anything after t. Everyone checks this by inspecting the causal mask β but hybrid stacks now mix attention with state-space scans, and a scan has no mask. Every mask can be correct while information leaks through scans, aggregations, or normalization.
βοΈ So we test the property directly. Two inputs identical except at the last position, two forward passes, compare each layer's prefix, report the first layer that moves. No training, no gradients, no accelerator β seconds on CPU.
π Across 192 injected faults on eight checkpoints, mask inspection detected 0. The per-layer audit localized 192/192 to the exact layer.
π― Then we read the source before running anything. In transformers 5.7.0, the reference chunked scan reduces the inter-chunk recurrence over the input chunk axis; zamba2 and nemotron_h reduce over the output chunk axis. One axis. The dynamic audit confirmed the prediction exactly: Zamba2-1.2B leaks from length 256, its declared chunk size, and Nemotron-H-8B from 128, its declared chunk size. Bamba, Falcon-H1, Granite-4.0-H, Mamba2 and RecurrentGemma came back clean.
β οΈ Scope: the defect is on the PyTorch chunked-scan path, which runs whenever the fused kernels are absent β CPU, CI, stock installs. We could not build those kernels, so the fast path is untested and open. That caveat cuts both ways: a model can pass every fused-kernel test and still leak the moment it runs without them.
π§ͺ AX-RAY now carries this as its own axis. 39 models scored across causal, white-box and behavioral axes: 21 A, 3 B, 1 C, 14 F β with exactly 2 Causal-LEAK verdicts, the two the paper predicted. Badges separate a weights-level audit from an API-only one, so the two never get read as the same claim.
π https://arxiv.org/abs/2608.22876
π¬ FINAL-Bench/AX-RAY
π€ The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models (2608.22876)
An autoregressive model must not let position t depend on anything after t. Everyone checks this by inspecting the causal mask β but hybrid stacks now mix attention with state-space scans, and a scan has no mask. Every mask can be correct while information leaks through scans, aggregations, or normalization.
βοΈ So we test the property directly. Two inputs identical except at the last position, two forward passes, compare each layer's prefix, report the first layer that moves. No training, no gradients, no accelerator β seconds on CPU.
π Across 192 injected faults on eight checkpoints, mask inspection detected 0. The per-layer audit localized 192/192 to the exact layer.
π― Then we read the source before running anything. In transformers 5.7.0, the reference chunked scan reduces the inter-chunk recurrence over the input chunk axis; zamba2 and nemotron_h reduce over the output chunk axis. One axis. The dynamic audit confirmed the prediction exactly: Zamba2-1.2B leaks from length 256, its declared chunk size, and Nemotron-H-8B from 128, its declared chunk size. Bamba, Falcon-H1, Granite-4.0-H, Mamba2 and RecurrentGemma came back clean.
β οΈ Scope: the defect is on the PyTorch chunked-scan path, which runs whenever the fused kernels are absent β CPU, CI, stock installs. We could not build those kernels, so the fast path is untested and open. That caveat cuts both ways: a model can pass every fused-kernel test and still leak the moment it runs without them.
π§ͺ AX-RAY now carries this as its own axis. 39 models scored across causal, white-box and behavioral axes: 21 A, 3 B, 1 C, 14 F β with exactly 2 Causal-LEAK verdicts, the two the paper predicted. Badges separate a weights-level audit from an API-only one, so the two never get read as the same claim.
π https://arxiv.org/abs/2608.22876
π¬ FINAL-Bench/AX-RAY
π€ The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models (2608.22876)
- 13 replies
upvoted a collection 8 days ago