How does Nanbeige4.1 3B rank among AI models?
Nanbeige4.1 3B is a superseded version and is not on the current board as of 24 October 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.
Nanbeige·#224 of 501 in the all-versions archive
Nanbeige4.1 3B is a language model from Nanbeige. It ranks #224 of 501 in ModelCap's all-versions archive, with an Index score of 46.1, modeled from the publisher's launch results against measured models. Its score range of 33.2–59.0 spans positions #134–#325. Its weights are openly downloadable.
Figures as of 24 Oct 2026, 19:29 UTC · download the public dataset · methodology
ModelCap Index · All-versions archive
46.1#224
Modeled from the publisher's launch results against measured models · range 33.2–59.0
Superseded by Nanbeige4.2 3B. It no longer holds a current-board position; its all-versions archive rank is #224.
OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.
Input
Self-hosted
weights only · no listed API price
Output
Self-hosted
weights only · no listed API price
Context
—
tokens
Providers
0
endpoints
Providers
Uptime measured over the last 30 minutesCurrent provider status is unavailable.
Reported evaluation leads (3)
Not independent measurementStructured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. Rows marked as used were laddered against independently measured peers inside the launch-card channel of this model's modeled placement, with the replay-measured optimism haircut applied; the others played no part.
Other versions (1)
ModelCap Index · All-versions archive
Methodology46.1
Modeled from the publisher's launch results against measured models
All-versions archive
#224 of 501
- Score range
- 33.2–59.0
- Rank range
- #134–#325
Technical details
- Public rank basis
- Modeled · peer benchmarks (architecture)
- Evidence label
- Modeled · peer benchmarks · global-corpus-prior over 211 held-out anchors (19%); launch card against 2 resolved peers on 7 rows (81%); exceeds every named peer on 6 of 7 rows; optimism haircut 3 from cross-lab-probe; shrunk 1.4 up toward the measured corpus
- Index support
- 35.0% · limited
- Identity binding
- Exact catalogue product · nanbeige/Nanbeige/Nanbeige4.1-3B · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Nanbeige/Nanbeige4.1-3B@9c4555c37921c0982af8fffeee1e0a6e6b953c4f (not the evaluation revision)
- Index observations used
- 0
- Qualified Index evidence point
- 46.1
How this position was produced · fused launch placement
No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.
- Fused estimate
- 46.1 ± 10.1
- Independent share
- 0%
- Shrink toward corpus
- +1.4
- Peer ceiling share
- 86%
- Optimism haircut
- −3.0 points · cross lab probe, 1 probe
- Method
- precision-weighted-v1
- · Launch card row aime-2026-i: claims above every resolved peer
- · Launch card row bfcl-v-4: claims above every resolved peer
- · Launch card row gpqa: claims above every resolved peer
- · Launch card row hle: claims above every resolved peer
- · Launch card row hmmt-nov: claims above every resolved peer
- · Launch card row imo-answer-bench: inside the resolved peer range
- · Launch card row tau-2-bench: claims above every resolved peer
Bayesian Evidence Score · measured evidence input only
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
- Observed capability
- —
- Evidence status
- No admitted measured evidence
- General preference
- —
- Coding
- —
- Agents & tools
- —
- Reasoning
- —
- Evidence breadth
- 0%
- Evidence coverage
- 0%
Market and catalogue signals · secondary, never the language Index rank
- Usage (OpenRouter popularity)
- —
- Liquidity (providers × uptime)
- —
- Open reach (HF downloads)
- 65.1
- Surface (context / tools / modalities)
- 0.0
- Freshness
- 37.6
- · HF 30d downloads 3673
- · Catalogue surface
- · First seen 2026-02-10
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Experimental capability estimate
Estimate policy9.5
0.0–24.5 uncertainty interval
- Confidence
- 76%
- Training support
- 221 models · 129 lineages
- Out-of-domain check
- in domain
- Feature coverage
- 71%
- Lineage-held-out error
- 8.3 MAE
Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.
Deployment readiness
Metadata index52.4
partial · 56% metadata coverage
- Artifact reproducibility
- 100.0
- Access & legal clarity
- 100.0
- Deployability
- 8.0
- Evaluation provenance
- 0.0
Not yet published: a current serving provider, measured provider uptime, published provider pricing, declared context and output limits, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market activity
Venue coverage- Market Gravity
- 11.6
- OpenRouter weekly popularity
- Not listed
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
Arena preference
No matched Arena rating
This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.
Market Gravity breakdown
- Usage55%
- 0.0
- Liquidity25%
- 0.0
- Open reach15%
- 65.1
- Freshness5%
- 37.6
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Specification
- Model ID
Nanbeige/Nanbeige4.1-3B- Declared output cap
- Unknown
OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
- Inputs
- Text
- Outputs
- Text
- Cached input tokens
- Not offered
- First seen on OpenRouter
- 10 Feb 2026
Capabilities
- Not supported: Reasoning
- Not supported: Tool use
- Not supported: Structured output
- Not supported: Response format
- Not supported: Moderated
Weights & access
Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.
- Access
- Open weights
- Licence
- apache-2.0
- Pinned revision
- 9c4555c37921
- Parameters
- 3.9B
- Architecture
- LlamaForCausalLM
- Model type
- llama
- Hugging Face downloads (30d)
- 4K
- Downloads (all time)
- 1.4M
- Likes
- 1K
- Repository
- Nanbeige/Nanbeige4.1-3B
- Repository updated
- 25 Mar 2026, 01:56 UTC
- Base lineage
- Nanbeige/Nanbeige4-3B-Base
Benchmark leaderboards featuring Nanbeige4.1 3B
All leaderboardsNanbeige4.1 3B: common questions
How much does Nanbeige4.1 3B cost per 1M tokens?
No live API price is listed for Nanbeige4.1 3B in the current snapshot as of 24 October 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.
Is Nanbeige4.1 3B open-weight?
Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is Nanbeige/Nanbeige4.1-3B on Hugging Face.
Which benchmarks has Nanbeige4.1 3B been evaluated on?
Nanbeige4.1 3B has published results on 3 public boards tracked by ModelCap as of 24 October 2026: AA Terminal-Bench 2.1 1.1% (#116 of 124), AA τ²-Bench Telecom 21.6% (#101 of 152) and AA Humanity's Last Exam 10.9% (#145 of 265). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.
When was Nanbeige4.1 3B released?
Nanbeige4.1 3B first appeared in the catalogue on 10 Feb 2026. It has since been superseded by Nanbeige4.2 3B. Rank and price movements since then are recorded on the site's changes feed.