Skip to main content
BenchLM
Data

Data as of November 21, 2026 · How the score is built

Decision readingpplx-embed-v2-late-9b is tracked, but not publicly ranked yet. The profile exposes 2 sourced benchmark rows and leaves unsupported fields blank until a published record exists.

Email me when its price, rank or availability changes.

Capability

Unranked

field median 47.5Not eligible for a public rank

Price

Self-hosted; infrastructure cost varies

input median $0.60No comparable first-party hosted token rate

Speed

Not measured

field median 93.5 tok/sTime to first token not measured

Context

4096 tokenstokens

field median 256,000Maximum output length is tracked separately

Decision snapshot

How much published evidence this model has, where that evidence is strongest, and what to validate before choosing it. It has no public rank, so no field position is shown.

Strongest published evidence

Published rows are visible, but no category has enough eligible evidence for a comparative rank.

Validate before choosing

2 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 2 displayable benchmark rows

Benchmark ledger

Every result says who ran the test. For this model, Perplexity ran all 2. External signals opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank
Not ranked yet
No benchmark-run or independent results yet
Reported by Perplexity
2
Shown with that label
Run by a benchmark
0
None yet
Independent runs
0
None yet
External signals2 rows
External signals benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
ViDoRe V3 Image (Perplexity report)65.2%

Best verified: pplx-embed-v2-late-9b · 65.2%

GapHighest listedReported by PerplexityShown only
ViDoRe V3 Markdown (Perplexity report)64.7%

Best verified: pplx-embed-v2-late-9b · 64.7%

GapHighest listedReported by PerplexityShown only

Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Oct 7, 2026 · you are here

    pplx-embed-v2-late-9b

    Not publicly ranked · Price not listed

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

Weights model ID
perplexity-ai/pplx-embed-v2-late-9bPerplexity pplx-embed-v2-late-9b model card
Maximum output
128-dimensional vector per retained token; no generated textPerplexity pplx-embed-v2-late-9b model card
Knowledge cutoff
Not sourced yet
Parameters
8.39B total (checkpoint metadata); 7.4B active (model card)Hugging Face checkpoint parameter metadata
Availability
Hugging Face · Self-hosted inferencePerplexity pplx-embed-v2-late-9b model card
Cloud regions
Not tracked yet
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing recordPerplexity pplx-embed-v2-late-9b model card
Self-host
Open weights available; hardware estimate not sourced
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

We track pplx-embed-v2-late-9b, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.

pplx-embed-v2-late-9b is a open weight model with a 4096 tokens context window. No explicit reasoning mode is documented in this profile.

Self-hosted Sentence Transformers MultiVectorEncoder weights. Text and image inputs are supported in separate batches; mixed text-plus-image inputs are not supported. Output is token-level embeddings, not generated text. Queries are capped at 1,024 tokens and documents at 4,096 tokens in the published encoding config.

Perplexity released pplx-embed-v2-late-9b on October 7, 2026, with MIT-licensed weights. It is a multilingual text and image retriever built on Qwen3.5 with bidirectional attention. The checkpoint has 8.39B total parameters in Hugging Face metadata; the model card reports 7.4B active parameters. Its Sentence Transformers config limits queries to 1,024 tokens and documents to 4,096 tokens; the trunk positional limit of 262,144 is not the published encoding limit. Encode text and images in separate batches; mixed text-plus-image inputs are not supported. Perplexity reports public ViDoRe V3 nDCG@10 on a 0–100 scale. Image and Markdown retrieval use separate input representations. These provider-reported results remain display-only and do not establish general LLM capability scores. The two models share a multi-vector embedding space; each retained token has a 128-dimensional vector, and query–document pairs use MaxSim scoring.

pplx-embed-v2-late-9b sits in the Perplexity Embed v2 Late family with pplx-embed-v2-late-0.6b. 2 of 952 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Last updated November 21, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.

Estimate VRAM from known parameters

Questions

How does pplx-embed-v2-late-9b perform overall in AI benchmarks?

pplx-embed-v2-late-9b has 2 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.

Is pplx-embed-v2-late-9b open source?

pplx-embed-v2-late-9b is an open-weight model from Perplexity. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Which sibling models are related to pplx-embed-v2-late-9b?

pplx-embed-v2-late-9b belongs to the Perplexity Embed v2 Late family. Related tracked variants include pplx-embed-v2-late-0.6b. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does pplx-embed-v2-late-9b have full benchmark coverage on BenchLM?

No. pplx-embed-v2-late-9b currently has 2 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of pplx-embed-v2-late-9b?

pplx-embed-v2-late-9b has a documented context window of 4096 tokens. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare pplx-embed-v2-late-9b with every tracked model1034 comparisons