Qwen3 Embedding 8B

Released
2025-06-06
Last refreshed
2026-06-29
Status
Researched 181d ago
Open sourceCommercial use: permitted
Alibaba releases · 52 in the last 12 monthsChangelog →
Specifications
Released
2025-06-06
Context
32K
Parameters
8B
Architecture
Decoder Only
Specialization
embedding
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
-
Input / 1M
$0.070

Cheapest of 1 route · Novita AI

Providers(1)

About

Qwen3 Embedding 8B is Alibaba's large multilingual text embedding model from the Qwen3 generation, supporting 119 languages. Open-sourced under Apache 2.0. Achieves SOTA performance on MTEB multilingual benchmarks. Part of the Qwen3-Embedding series released June 2025.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.070-
ServerlessPartial

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
75.22MTEB(eng, v2)Observed 2026-10-17
Harness: mteb 2.26.6 leaderboard aggregation, Mean (Task) over 41 tasks
Evaluator: Alibaba Qwen (model card; MTEB leaderboard snapshot)
Confidence: self-reported
Notes: MTEB(eng, v2) Mean (Task) 75.22 as published on the Qwen3-Embedding model card (standing rule: the model's own card wins). The leaderboard aggregation of embeddings-benchmark/results @ 4bb41dd gives 75.23 on 2026-10-17 (rounding only). Source: Qwen3-Embedding card; MTEB (embeddings-benchmark/results, CC0). Retrieved 2026-10-17.
70.58MTEB(Multilingual, v2)Observed 2026-10-17
Harness: mteb 2.26.6 leaderboard aggregation, Mean (Task) over 131 tasks
Evaluator: Alibaba Qwen (model card; MTEB leaderboard snapshot)
Confidence: self-reported
Notes: MTEB(Multilingual, v2) Mean (Task) 70.58 as published on the Qwen3-Embedding model card (standing rule: the model's own card wins). The leaderboard aggregation of embeddings-benchmark/results @ 4bb41dd gives 70.58 on 2026-10-17 (rounding only). Source: Qwen3-Embedding card; MTEB (embeddings-benchmark/results, CC0). Retrieved 2026-10-17.

Migration checks

No linked migration route is available for this model yet.