Nex-N2-Pro

Official publisher releaseOpen weights

Nex AGI·#63 of 504 in the all-versions archive

Nex-N2-Pro is a language model from Nex AGI. It ranks #63 of 504 in ModelCap's all-versions archive, with an Index score of 74.0, modeled from the publisher's launch results against measured models. Its score range of 66.6–81.5 spans positions #14–#107. It reads up to 262K tokens of context, and its weights are openly downloadable.

Figures as of 6 Nov 2026, 14:10 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive

74.0#63

Modeled from the publisher's launch results against measured models · range 66.6–81.5

Market Gravity

8.8

Secondary market signal

Superseded by Nex-N2.5-Pro. It no longer holds a current-board position; its all-versions archive rank is #63.

Input

Self-hosted

weights only · no listed API price

Output

Self-hosted

weights only · no listed API price

Context

262K

tokens

Providers

endpoints

Providers

Uptime measured over the last 30 minutes

No provider is currently serving this model.

Reported evaluation leads (1)

Not independent measurement

Structured 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.

Dataset / task	Metric	Value	Revision	Provenance
internlm/WildClawBench overall	—	53.5	Unpinned `not published`	Reported Not used in launch estimate

Other versions (1)

Nex-N2.5-ProLanguage board #27last month

ModelCap Index · All-versions archive

Methodology

74.0

Modeled from the publisher's launch results against measured models

All-versions archive

#63 of 504

Score range: 66.6–81.5
Rank range: #14–#107

Technical details

Public rank basis: Modeled · peer benchmarks (architecture)
Evidence label: Modeled · peer benchmarks · global-corpus-prior over 210 held-out anchors (6%); launch card against 6 resolved peers on 7 rows (94%); optimism haircut 0 from cross-lab-probe; shrunk 1.3 toward the measured corpus
Index support: 35.0% · limited
Identity binding: Exact catalogue product · nex-agi/nex-agi/nex-n2-pro · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata nex-agi/Nex-N2-Pro@e7e4a4a29eb46a41a730d0b283ec5af0f16185d9 (not the evaluation revision)
Index observations used: 0
Qualified Index evidence point: 74.0

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: 74.0 ± 5.8
Independent share: 0%
Shrink toward corpus: -1.3
Peer ceiling share: 0%
Optimism haircut: None required · cross lab probe, 10 probes
Method: precision-weighted-v1

Channels fused into this model’s launch placement
Channel	Estimate	Share
Publisher corpus prior · not independent global-corpus-prior over 210 held-out anchors	53.5 ± 23.8	6%
Launch card against resolved peers · not independent launch card against 6 resolved peers on 7 rows	75.3 ± 6.0	94%

· Launch card row deepswe: inside the resolved peer range
· Launch card row gpqa-diamond: inside the resolved peer range
· Launch card row ifeval: inside the resolved peer range
· Launch card row swe-bench-pro: inside the resolved peer range
· Launch card row swe-bench-verified: inside the resolved peer range
· Launch card row terminal-bench-2-1: inside the resolved peer range
· Launch card row toolathlon: inside the resolved peer range

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): 39.7
Surface (context / tools / modalities): 90.3
Freshness: 56.3

· HF 30d downloads 866
· Catalogue: context 262144, reasoning, tools, modalities Text/Image
· First seen 2026-06-08

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

66.7

53.1–80.3 uncertainty interval

Excluded from rank

Confidence: 80%
Training support: 221 models · 129 lineages
Out-of-domain check: in domain
Feature coverage: 100%
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 index

54.2

partial · 56% metadata coverage

Not capability

Artifact reproducibility: 85.0
Access & legal clarity: 100.0
Deployability: 29.0
Evaluation provenance: 0.0

Not yet published: the base model it derives from, a current serving provider, measured provider uptime, published provider pricing, 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: 8.8
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%: 39.7
Freshness5%: 56.3

Specification

Model ID: nex-agi/nex-n2-pro
Context window: 262K tokens
Declared output cap: 236K 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
Outputs: Text
Tokenizer: Qwen3
Cached input tokens: $0.025 / 1M
First seen on OpenRouter: 8 Jun 2026

Capabilities

Supported: Reasoning
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: e7e4a4a29eb4
Parameters: 396.8B
Architecture: Qwen3_5MoeForConditionalGeneration
Model type: qwen3_5_moe
Hugging Face downloads (30d): 866
Downloads (all time): 13K
Likes: 377
Repository: nex-agi/Nex-N2-Pro
Repository updated: 11 Jun 2026, 09:43 UTC

Nex-N2-Pro: common questions

How does Nex-N2-Pro rank among AI models?

Nex-N2-Pro is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Nex-N2-Pro cost per 1M tokens?

No live API price is listed for Nex-N2-Pro in the current snapshot as of 6 November 2026 because no serving endpoint is published. ModelCap shows a price only when a provider currently lists one.

What is the context window of Nex-N2-Pro?

Nex-N2-Pro has a published context window of 262K tokens (262,144). The snapshot lists a 235,929 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 Nex-N2-Pro 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 nex-agi/Nex-N2-Pro on Hugging Face.

When was Nex-N2-Pro released?

Nex-N2-Pro first appeared in the catalogue on 8 Jun 2026. It has since been superseded by Nex-N2.5-Pro. Rank and price movements since then are recorded on the site's changes feed.