Skip to content
ModelCap

TCAndon Router

Current board #137Official publisher releaseOpen weights7d #136 → #137

Tencent·tencent/TCAndon-Router

TCAndon Router is ModelCap current-board rank #137 with Index 30.5 (Modeled · lineage), from the ModelCap Index as of 10 Sept 2026, 00:20 UTC.

TCAndon Router weight access is open weights, from ModelCap classification of published repository metadata as of 10 Sept 2026, 00:20 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
30.5#137
Inherited · 15% support · score interval 16.5–44.4
No admitted evaluation publication timestamp yet
Market Gravity
4.6Decreased by 0.3
Secondary market signal

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
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

ModelCap Index · Current board

Methodology
30.5
Modeled · lineage · finetune of Qwen/Qwen3-4B-Instruct-2507 · finetune (100%)
Current board
#137
Public rank basis
Modeled · lineage (lineage)
Index support
15.2% · limited
Index interval
16.5–44.4
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
No admitted evaluation publication timestamp
Identity binding
Exact catalogue product · tencent/tencent/TCAndon-Router · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata tencent/TCAndon-Router@14c2f8fdd32e4383bfbca22593f16723ccbacc01 (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
30.5
Verified lineage
Qwen/Qwen3-4B-Instruct-2507 · minus 1.2 ( finetune)
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
30.5 ± 10.9
Independent share
0%
Shrink toward corpus
0.0
Optimism haircut
None applied
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Verified lineage · not independent
finetune of Qwen/Qwen3-4B-Instruct-2507 · finetune
30.5 ± 10.9100%
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)
17.4
Surface (context / tools / modalities)
0.0
Freshness
39.2
  • · HF 30d downloads 166
  • · Catalogue surface
  • · First seen 2026-01-07

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 policy
31.6
12.1–51.2 uncertainty interval
Excluded from rank
Confidence
69%
Training support
188 models · 107 lineages
Out-of-domain check
in domain
Feature coverage
71%
Lineage-held-out error
10.3 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
52.4
partial · 56% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Missing: deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, deployability.declared-capacity, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
4.6
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

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
17.4

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
39.2

Time since first public availability, on a six-month half-life.

Specification

Context window
tokens
Max output
Inputs
Text
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
7 Jan 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
14c2f8fdd32e
Parameters
4.0B
Architecture
Qwen3ForCausalLM
Model type
qwen3
Hugging Face downloads (30d)
166
Downloads (all time)
721
Likes
12
Repository updated
12 Jan 2026, 02:23 UTC

Compare TCAndon Router with

Pick any model

Alternatives to TCAndon Router, by the numbers

Ranked neighbours

Models within 3 places of #137 on the ModelCap Index.

Other ranked Tencent models

The same publisher's other current models with a public Index position.

TCAndon Router: common questions

How does TCAndon Router rank among AI models?

TCAndon Router holds ModelCap Index position #137 of 166 ranked language models as of 10 September 2026, with an Index score of 30.5 (interval 16.5–44.4); evidence: modeled · lineage. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does TCAndon Router cost per 1M tokens?

No live API price is listed for TCAndon Router in the current snapshot as of 10 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is TCAndon Router 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 tencent/TCAndon-Router on Hugging Face.

Which benchmarks has TCAndon Router been evaluated on?

TCAndon Router's Index position rests on the evidence listed on this page; it has no result on the public boards ModelCap tracks as separate leaderboards as of 10 September 2026. The evidence panel names each source and its publication date.

How does TCAndon Router compare with Privasis Cleaner 4B?

TCAndon Router ranks #137 (Index 30.5) and Privasis Cleaner 4B ranks #136 (Index 30.5) on the ModelCap Index as of 10 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was TCAndon Router released?

TCAndon Router first appeared in the catalogue on 7 Jan 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.