Skip to content
ModelCap

Qwen4 Max

NewPreliminaryNo linked weights3d #35 → #36

Qwen·#36 of 371 on the current board·cheaper than #29 GPT-6.2 Sol

Qwen4 Max is a language model from Qwen. It ranks #36 of 371 on ModelCap's current board, with a preliminary Index score of 72.8, partly measured on public benchmarks and partly modeled. Its score range of 61.7–83.9 spans positions #7–#72. It is listed at $1.42 per million input tokens and $4.27 per million output tokens from one provider. It reads up to 1M tokens of context, with no downloadable weights linked in the current source data.

Figures as of 19 Nov 2026, 05:16 UTC · download the public dataset · methodology

ModelCap Index · Current board
72.8#36
Partly measured on public benchmarks and partly modeled · range 61.7–83.9
Evidence as of 18 Nov 2026, 00:00 UTC
Market Gravity
37.4Increased by 1.3
Secondary market signal
Input
$1.42
per 1M tokens
Output
$4.27
per 1M tokens
Context
1M
tokens
Providers
1
endpoint

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Alibaba$1.42$4.271M—100.0%

Reasoning efforts

Best supported result can inform ModelCap

Published Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.

EffortAgent scoreSource rankSampleSource
X-High
Qwen4-Max (xHigh)
7.27%
CI 5.9–8.6%
#181.7M obs
15K sessions
LMArena Agent
Match 100%

Other versions (5)

ModelCap Index · Current board

Methodology
72.8
Partly measured on public benchmarks and partly modeled
Current board
#36 of 371

Preliminary. Measured on 1 public benchmark so far, with limited support. Expect the score and position to move as more boards report. What this label means

Score range
61.7–83.9
Rank range
#7–#72
Evidence as of
18 Nov 2026, 00:00 UTC
Benchmarks used
LMArena Agent
Technical details
Public rank basis
Measured · blended (measured)
Evidence label
Measured · blended · 1 reported rows against measured corpus ladders (22%); publisher-corpus-prior over 214 held-out anchors (14%); opens above measured predecessor qwen/qwen3.8-max on same-family ordering evidence (52%); 1 specialist-board observation at 2.5% support (12%); shrunk 3.8 toward the measured corpus
Index support
2.5% · weak
Identity binding
Exact catalogue product · qwen/qwen/qwen4-max · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
1
Qualified Index evidence point
72.8
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
72.8 ± 8.7
Independent share
12%
Shrink toward corpus
-3.8
Optimism haircut
None applied
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Corpus ladder · not independent
1 reported rows against measured corpus ladders
75.7 ± 18.522%
Publisher corpus prior · not independent
publisher-corpus-prior over 214 held-out anchors
50.3 ± 22.914%
Family succession · not independent
opens above measured predecessor qwen/qwen3.8-max on same-family ordering evidence
78.9 ± 12.052%
Specialist board measurement
1 specialist-board observation at 2.5% support
67.9 ± 25.312%
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
67.9
Evidence status
provisional · 4% mass
General preference
—
Coding
—
Agents & tools
67.9
Reasoning
—
Evidence breadth
5%
Evidence coverage
3%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
31.1
Liquidity (providers × uptime)
31.3
Open reach (HF downloads)
—
Surface (context / tools / modalities)
100.0
Freshness
98.8
  • · OpenRouter popularity #56
  • · 1 live provider
  • · Catalogue: context 1000000, reasoning, tools, modalities Text/Image/Video
  • · First seen 2026-11-16

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
37.6
limited · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
80.0
Evaluation provenance
37.9

Not yet published: a pinned repository revision, the architecture and model type, a parameter count, safetensors weight metadata, the base model it derives from, a declared licence, a link to the licence terms, 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
37.4
OpenRouter weekly popularity
#56 of 345

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%
31.1

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
31.3

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%
98.8

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

Specification

Model ID
qwen/qwen4-max
Context window
1M tokens
Declared output cap
131K tokens

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, Image, Video
Outputs
Text
Tokenizer
Qwen
Cached input tokens
$0.071 / 1M
First seen on OpenRouter
16 Nov 2026

Capabilities

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

Compare Qwen4 Max with

Pick any model

Benchmark leaderboards featuring Qwen4 Max

All leaderboards
Public benchmark boards on which Qwen4 Max has a published result
LeaderboardScoreSource rankConfigurationPublished
LMArena Agent leaderboardLMArena7.3%5.9%–8.6%#18 of 68X-High18 Nov 2026
Artificial Analysis Intelligence IndexArtificial Analysis42.9#37 of 125Reasoning16 Nov 2026

Alternatives to Qwen4 Max, by the numbers

Ranked neighbours

Models within 3 places of #36 on the ModelCap Index.

Cheaper at a similar or higher Index

Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).

Other ranked Qwen models

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

Qwen4 Max: common questions

How does Qwen4 Max rank among AI models?

Qwen4 Max holds ModelCap Index position #36 of 371 ranked language models as of 19 November 2026, with an Index score of 72.8 (interval 61.7–83.9); evidence: measured · blended. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does Qwen4 Max cost per 1M tokens?

Qwen4 Max is listed at $1.42 per 1M input tokens and $4.27 per 1M output tokens as of 19 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $4.99 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Qwen4 Max?

Qwen4 Max has a published context window of 1M tokens (1,000,000). The snapshot lists a 131,072 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.

Is Qwen4 Max open-weight?

No linked weights. No downloadable model weights are linked in the current source data. This does not identify every API or chat product that offers the model.

Which API providers serve Qwen4 Max?

One provider serves Qwen4 Max through OpenRouter as of 19 November 2026: Alibaba. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has Qwen4 Max been evaluated on?

Qwen4 Max has published results on 2 public boards tracked by ModelCap as of 19 November 2026: LMArena Agent 7.3% (#18 of 68) and AA Intelligence Index 42.9 (#37 of 125). 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.

How does Qwen4 Max compare with Qwen3.8 27B?

Qwen4 Max ranks #36 (Index 72.8) and Qwen3.8 27B ranks #68 (Index 63.1) on the ModelCap Index as of 19 November 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was Qwen4 Max released?

Qwen4 Max first appeared in the catalogue on 16 Nov 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.