Skip to content
ModelCap

Agnes 3.0 Flash

Current board #77Official publisher releaseNewOpen weights

Agnes AI·Agnes-AI/Agnes-3.0-Flash

Agnes 3.0 Flash is ModelCap current-board rank #77 with Index 51.8 (Modeled · peer benchmarks), from the ModelCap Index as of 12 Sept 2026, 13:09 UTC.

Agnes 3.0 Flash weight access is open weights, from ModelCap classification of published repository metadata as of 12 Sept 2026, 13:09 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
51.8#77
Estimated · 28% support · score interval 43.0–60.6
No admitted evaluation publication timestamp yet
Market Gravity
6.4
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
51.8
Modeled · peer benchmarks · calibrated architecture-and-release-era fallback from static public metadata
Current board
#77
Public rank basis
Modeled · peer benchmarks (architecture)
Index support
28.4% · limited
Index interval
43.0–60.6
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 · agnes-ai/Agnes-AI/Agnes-3.0-Flash · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Agnes-AI/Agnes-3.0-Flash@8f0c484c363cdda8384195be4a5f7730f3915bde (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
51.8
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
51.8 ± 6.8
Independent share
0%
Shrink toward corpus
+0.1
Peer ceiling share
20%
Optimism haircut
−0.3 points · cross lab probe, 5 probes
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Publisher corpus prior · not independent
global-corpus-prior over 188 held-out anchors
52.9 ± 22.210%
Launch card against resolved peers · not independent
launch card against 2 resolved peers on 5 rows
51.7 ± 7.291%
  • · Launch card row aa-lcr: claims below every resolved peer
  • · Launch card row aa-omniscience: claims above every resolved peer
  • · Launch card row gpqa-diamond: claims below every resolved peer
  • · Launch card row ifbench: claims below every resolved peer
  • · Launch card row scicode: claims below 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)
9.5
Surface (context / tools / modalities)
15.0
Freshness
99.7
  • · HF 30d downloads 34
  • · Catalogue: modalities Text/Image
  • · First seen 2026-09-11

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
43.2
24.5–61.9 uncertainty interval
Excluded from rank
Confidence
68%
Training support
194 models · 110 lineages
Out-of-domain check
in domain
Feature coverage
71%
Lineage-held-out error
10.0 MAE

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

Deployment readiness

Metadata index
47.9
partial · 52% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Missing: artifactReproducibility.base-lineage, 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
6.4
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%
9.5

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

Freshness5%
99.7

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

Specification

Context window
tokens
Max output
Inputs
Text, Image
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
11 Sept 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
8f0c484c363c
Parameters
33.1B
Architecture
AgnesForConditionalGeneration
Model type
agnes
Hugging Face downloads (30d)
34
Downloads (all time)
34
Likes
75
Repository updated
11 Sept 2026, 15:56 UTC

Compare Agnes 3.0 Flash with

Pick any model

Alternatives to Agnes 3.0 Flash, by the numbers

Ranked neighbours

Models within 3 places of #77 on the ModelCap Index.

Agnes 3.0 Flash: common questions

How does Agnes 3.0 Flash rank among AI models?

Agnes 3.0 Flash holds ModelCap Index position #77 of 187 ranked language models as of 12 September 2026, with an Index score of 51.8 (interval 43.0–60.6); evidence: modeled · peer benchmarks. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does Agnes 3.0 Flash cost per 1M tokens?

No live API price is listed for Agnes 3.0 Flash in the current snapshot as of 12 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is Agnes 3.0 Flash 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 Agnes-AI/Agnes-3.0-Flash on Hugging Face.

Which benchmarks has Agnes 3.0 Flash been evaluated on?

Agnes 3.0 Flash'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 12 September 2026. The evidence panel names each source and its publication date.

How does Agnes 3.0 Flash compare with Ling 3.0 Flash Fin?

Agnes 3.0 Flash ranks #77 (Index 51.8) and Ling 3.0 Flash Fin ranks #78 (Index 51.3) on the ModelCap Index as of 12 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was Agnes 3.0 Flash released?

Agnes 3.0 Flash first appeared in the catalogue on 11 Sept 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.