llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Infgrad model product

Jasper-Token-Compression-600M

Jasper-Token-Compression-600M is an embedding model from Infgrad ranked on MTEB.

Updated Sep 8, 2026. Default version: Jasper-Token-Compression-600M

LLMBoard Embedding Score89.2Jasper-Token-Compression-600M
Coverage85%5 benchmark families
Context window32.8KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Jasper-Token-Compression-600M Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Jasper-Token-Compression-600M LLMBoard score breakdown

Jasper-Token-Compression-600M Benchmark Results

Benchmark scores for Jasper-Token-Compression-600M.

5 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMTEB English v2 Semantic SimilarityScore88.79%Rank03Participants211Percentile99.05%EvidenceAEvaluatedN/A
BenchmarkMTEB English v2 ClassificationScore90.25%Rank05Participants257Percentile98.44%EvidenceAEvaluatedN/A
BenchmarkMTEB English v2 RerankingScore50.60%Rank07Participants241Percentile97.50%EvidenceAEvaluatedN/A
BenchmarkMTEB English v2 RetrievalScore66.19%Rank08Participants212Percentile96.68%EvidenceAEvaluatedN/A
BenchmarkMTEB English v2 ClusteringScore59.44%Rank12Participants217Percentile94.91%EvidenceAEvaluatedN/A

Jasper-Token-Compression-600M Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Jasper-Token-Compression-600M Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Jasper-Token-Compression-600M Runtime Performance

Provider-specific output speed and catalog latency for Jasper-Token-Compression-600M. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Jasper-Token-Compression-600M Specifications

Technical details for the model's default version.

Version
Jasper-Token-Compression-600M
Released
Nov 14, 2025
Knowledge cutoff
Unknown
Parameters
607M
Context window
32.8K
Max output
N/A
Inputs
text
Outputs
embedding
Open weights
Yes
License
mit

Jasper-Token-Compression-600M Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionJasper-Token-Compression-600MReleasedNov 14, 2025LLMBoard89.23Parameters607MContext32.8KMax outputN/AOpen weightsYesLicensemit

Models similar to Jasper-Token-Compression-600M

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#91-29.91
IN

stella-base-en-v2

Infgrad

59.32 LLMBoard

Details
#4-0.16
AC

Qwen3-Embedding-8B

Alibaba Cloud / Qwen Team

89.07 LLMBoard

Details
#2+0.66
JC

ingot-8b-r3

Jcorners

89.89 LLMBoard

Details
#5-0.82
BS

Seed1.5-Embedding

Bytedance Seed

88.41 LLMBoard

Details
#1+0.95
KL

QZhou-Embedding

Kingsoft Llm

90.18 LLMBoard

Details
#6-1.54
AC

Qwen3-Embedding-4B

Alibaba Cloud / Qwen Team

87.69 LLMBoard

Details

What is Jasper-Token-Compression-600M?

Key information about Jasper-Token-Compression-600M and its available data.

Jasper-Token-Compression-600M is an embedding model developed by Infgrad. It is ranked on MTEB.

Data as of 2026-09-08.

FAQ

Common questions about Jasper-Token-Compression-600M.

When was Jasper-Token-Compression-600M released?

Jasper-Token-Compression-600M's default version was released on Nov 14, 2025.

How much does Jasper-Token-Compression-600M cost?

No official standard PAYG price is currently available for Jasper-Token-Compression-600M.

Who created Jasper-Token-Compression-600M?

Jasper-Token-Compression-600M was created by Infgrad.

What is the context window for Jasper-Token-Compression-600M?

The default version has a 32.8K token context window.

Is Jasper-Token-Compression-600M open weight?

Yes. The default version is marked as open weight under mit.

How many API providers offer Jasper-Token-Compression-600M?

No provider offering is currently linked to the default version.

Browse runtime rankings