Harrier OSS v1 270M
Harrier OSS v1 270M is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.
Advancing the state-of-the-art in AI and computing.
No tracked provider pricing is available yet.
About
Lightweight variant of Microsoft's Harrier open-source multilingual embedding family, released March 30, 2026. Decoder-only architecture based on Gemma 3. Produces 640-dimensional embeddings. MTEB-v2 score: 66.5. Supports 94+ languages. Trained with contrastive learning and knowledge distillation. MIT license. Best choice for latency-sensitive deployments.
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)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 66.55 | MTEB(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) 66.55 over 131 tasks; Mean (TaskType) 56.90. 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. Microsoft's harrier-oss-v1 card reports 66.5 (1 dp), consistent with this value. |
Migration checks
No linked migration route is available for this model yet.
Advancing the state-of-the-art in AI and computing.
No tracked provider pricing is available yet.