Granite Embedding 311M Multilingual R2

Released
2026-04-29
Last refreshed
2026-09-03
Status
Researched 180d ago
Open sourceCommercial use: permitted

Granite Embedding 311M Multilingual R2 is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.

IBM Research releases · 25 in the last 12 months · this family litChangelog →
Specifications
Released
2026-04-29
Context
32K
Parameters
311M
Specialization
embedding
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by
IBM Research

Creating reliable and adaptable AI solutions

Armonk, New York, United States
Founded 1945
Website
Pricing

No tracked provider pricing is available yet.

About

IBM Granite Embedding 311M Multilingual R2 is a text embedding model supporting 200+ languages (with explicit training for 52 languages and programming code). Produces 768-dimensional embeddings. Improved from R1 via layer pruning and continued distillation training, yielding a +14.5 point average gain over the previous granite-embedding-107m-multilingual. Designed for semantic search, retrieval-augmented generation, and cross-lingual retrieval. Apache 2.0 license. Part of the Granite 4.1 family release.

Providers

No active provider routes are tracked for this model yet.

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(1)

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
MMTEB Multilingual v2
55.96MTEB(Multilingual, v2)Observed 2026-10-17
Harness: mteb 2.26.6 leaderboard aggregation, Mean (Task) over 131 tasks
Evaluator: MTEB (embeddings-benchmark/results)
Confidence: confirmed
Notes: MTEB(Multilingual, v2) Mean (Task) 55.96 over 131 tasks; Mean (TaskType) 49.35. Computed with the leaderboard's own code (mteb 2.26.6 Benchmark summary table) from embeddings-benchmark/results @ 4bb41dd (2026-10-17). Source: MTEB (embeddings-benchmark/results, CC0). Retrieved 2026-10-17.
Source

Migration checks

No linked migration route is available for this model yet.