Skip to content
ModelCap

Qwen3.8 2.4T A95B

Current board #8Official publisher releaseNewRestricted license7d #36 → #8

Qwen·qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is ModelCap current-board rank #8 with Index 77.2 (Measured), from the ModelCap Index as of 14 Aug 2026, 00:24 UTC.

Qwen3.8 2.4T A95B listed OpenRouter input price is $2.00 per 1M tokens and listed output price is $6.00 per 1M tokens, from OpenRouter listed prices as of 14 Aug 2026, 00:24 UTC.

Qwen3.8 2.4T A95B has a published context limit of 1M tokens in the ModelCap catalogue as of 14 Aug 2026, 00:24 UTC.

Qwen3.8 2.4T A95B has 5 published OpenRouter serving endpoints, from OpenRouter as of 14 Aug 2026, 00:24 UTC.

Qwen3.8 2.4T A95B weight access is restricted license, from ModelCap classification of published repository metadata as of 14 Aug 2026, 00:24 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
77.2#8
Measured · 20% support · score interval 77.2–94.0
Evidence as of 14 Aug 2026, 00:24 UTC
Market Gravity
42.0Increased by 0.5
Secondary market signal
Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Context
1M
tokens
Providers
5
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DigitalOceanCheapest$2.00$6.00262K—100.0%
DeepInfrafp4$2.00$6.00262Kfp4—
Modalnvfp4$2.00$6.001Mnvfp499.76%
Alibaba$2.00$6.001M——
Together$2.50$6.251M——

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
fireworks-ai
live
——262K1276 ms76.8 tok/stools · structured

Reported evaluation leads (6)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
cais/hle
hle
—43.6
Unpinned
not published
Reported
Quarantined
datacurve/deep-swe
deep_swe
—56.6
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—92.6
Unpinned
not published
Reported
Quarantined
internlm/WildClawBench
overall
—56.2
Unpinned
not published
Reported
Quarantined
internlm/WildClawBench
avg_time
—708
Unpinned
not published
Reported
Quarantined
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
—67.7
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
77.2
Measured · 1 public benchmark observation across 1 board
Current board
#8
Public rank basis
Measured (measured)
Index support
20.0% · limited
Index interval
77.2–94.0
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
14 Aug 2026, 00:24 UTC
Identity binding
Exact catalogue product · qwen/qwen/qwen3.8-2.4t-a95b · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Qwen/Qwen3.8-2.4T-A95B@207bd685a7e3696cfaff12ded7c6a7ea0f88c996 (not the evaluation revision)
Index observations used
1
Qualified Index evidence point
85.6
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
85.6
Evidence status
provisional · 50% mass
General preference
85.6
Coding
—
Agents & tools
—
Reasoning
—
Evidence breadth
80%
Evidence coverage
20%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
10.9
Liquidity (providers × uptime)
94.3
Open reach (HF downloads)
—
Surface (context / tools / modalities)
85.0
Freshness
99.5
  • · OpenRouter popularity #164
  • · 5 live providers
  • · Catalogue: context 1010000, reasoning, tools
  • · First seen 2026-08-12

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

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.

Deployment readiness

Metadata index
80.7
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
97.2
Evaluation provenance
37.9

Missing: artifactReproducibility.base-lineage, 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
42.0
OpenRouter weekly popularity
#164 of 306

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%
10.9

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
94.3

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

Open reach15%
50.0

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

Freshness5%
99.5

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

Specification

Context window
1M tokens
Max output
262K tokens
Inputs
Text
Outputs
Text
Tokenizer
Qwen
Cached input tokens
$0.25 / 1M
First seen on OpenRouter
12 Aug 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
qwen3.8-max
Pinned revision
207bd685a7e3
Parameters
2446.2B
Architecture
Qwen3_5MoeForCausalLM
Model type
qwen3_5_moe_text
Hugging Face downloads (30d)
1K
Downloads (all time)
1K
Likes
782
Repository
Qwen/Qwen3.8-2.4T-A95B
Repository updated
12 Aug 2026, 10:24 UTC