Capability
Unranked
field median 56.2
Not eligible for a public rank
North Small Translate
Released Sep 10, 2026 — see all recent releases
Decision reading
North Small Translate is tracked, but not publicly ranked yet. The profile exposes 2 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of September 10, 2026 · How the score is built
Share or export
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.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
API rate not published
input median $1
No comparable first-party hosted token rate
Speed
Not measured
field median 86.5 tok/s
Time to first token not measured
Context
16Ktokens
field median 256,000
Maximum output length is tracked separately
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- AgenticNot measured
- CodingNot measured
- ReasoningNot measured
- KnowledgeNot measured
- MathNot measured
- Multilingual2/2 verified
- MultimodalNot measured
- Inst. FollowingNot measured
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- north-small-translate-1-0Cohere model documentation
- Context window
- 16KCohere model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Released September 10, 2026 as Cohere's first North-family translation model: a 218B-total / 25B-active mixture-of-experts model with a 16K input and 16K output context, text in and text out, and 50+ supported languages and locale variants. NVFP4 W4A16 weights are on Hugging Face under CC BY-NC 4.0 for research and non-commercial use; the Cohere API serves it as north-small-translate-1-0 (free until rate limits), and commercial licenses run through Cohere's Model Vault and RWS Language Weaver.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordCohere model documentation
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
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 parametersCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | Not ranked | Not available | 22% | 0 benchmarks | Not measured |
| CodingWeight 20%0 benchmarksNot measured | Not measured | Not ranked | Not available | 20% | 0 benchmarks | Not measured |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%2 benchmarksVerified | Score pending | Not ranked | Not available | 7% | 2 benchmarks | Verified |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Benchmark ledger
Multilingual opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Multilingual2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| WMT26WMT26 General Machine Translation (all languages) | Score83.6% | Versus best verified row Best verified: North Small Translate · 83.6% | GapBest verified | WeightDisplay only | Provider exact |
| Long-context translationLong-context translation evaluation (Cohere) | Score48.9% | Versus best verified row Best verified: North Small Translate · 48.9% | GapBest verified | WeightDisplay only | Provider exact |
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Sep 10, 2026 · you are here
North Small TranslateNot publicly ranked · Price not listed
Base entry
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 North Small Translate, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
North Small Translate is a open weight model with a 16K context window. No explicit reasoning mode is documented in this profile.
Released September 10, 2026 as Cohere's first North-family translation model: a 218B-total / 25B-active mixture-of-experts model with a 16K input and 16K output context, text in and text out, and 50+ supported languages and locale variants. NVFP4 W4A16 weights are on Hugging Face under CC BY-NC 4.0 for research and non-commercial use; the Cohere API serves it as north-small-translate-1-0 (free until rate limits), and commercial licenses run through Cohere's Model Vault and RWS Language Weaver.
Official exact-value snapshot from Cohere's September 10, 2026 North Small Translate launch post and the Cohere model documentation. BenchLM maps the two scored evaluations Cohere publishes: the WMT26 All Languages score (83.6, judged by GPT-5.6 Sol across 50+ languages) and Cohere's long-context translation evaluation (48.9, xCOMET-XL per paragraph over two book chapters translated in one call). Both are Cohere-run evaluations, so the rows are display-only and the model stays out of weighted ranking. Cohere also reports an Agentic mode at 84.36 on WMT26, regional averages (EU languages 82.17, non-EU Europe 81.24, South Asia 86.16), a commercial-configuration point of 80.1 at $0.000676 per task, and up to 1.4x higher output throughput than Gemma 4 31B on identical hardware; those claims stay descriptive.
2 of 434 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Radar
Full release historyNorth Small Translate release history
North Small Translate released
Cohere · Model release
Source confirmed
Radar confirmed these at the source. Use North Small Translate in your work? Explore Radar to follow supported changes and choose your alerts.
Frequently asked questions
How does North Small Translate perform overall in AI benchmarks?
North Small Translate 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 North Small Translate good for multilingual tasks?
North Small Translate has source-displayable benchmark coverage for multilingual tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is North Small Translate open source?
North Small Translate is an open-weight model from Cohere. 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.
Does North Small Translate have full benchmark coverage on BenchLM?
No. North Small Translate currently has 2 source-displayable rows across 434 tracked benchmark slots. 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 North Small Translate?
North Small Translate has a documented context window of 16K. 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 North Small Translate with every tracked model482 comparisons
Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch North Small Translate in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.