Is there an uncensored Command A?

Command A from Cohere is ranked 100 of 100 distinct active open-weight models in this Artificial Analysis snapshot.

Research and availability status

This is a research guide, not an available Wild West API model listing. No uncensored or abliterated Command A endpoint is confirmed here. An open-weight entry on AA does not establish that a derivative exists, works with a particular harness, or is hosted by Wild West API.

“Uncensored” describes reduced refusal behaviour or a service’s policy, not a standardized editing method. “Abliterated” refers to an intervention intended to reduce refusal-related behaviour through model-internal edits.

What rank 100 actually tells you

Command A scores above 0 of the 100 selected entries: a strictly-lower-score percentile of 0% in this snapshot. No other selected entry shares its exact index score. AA flags this index as estimated; treat the ordering as provisional.

It falls in the lower half of this top-100 selection. That does not make it unusable: a narrowly defined task can differ from the aggregate evaluation. However, this data alone supplies no efficiency, hardware or price reason to choose it over a stronger entry.

Base-model benchmark evidence

These are measurements attached to the evaluated base model, not an uncensored derivative. Missing values mean not reported here, never a zero score. Same-benchmark comparisons below use only entries with a reported measurement.

The highest numerical reported percentage for Command A is GPQA at 52.7%; the lowest is Terminal-Bench Hard at 0.8%. These are numerical extremes, not evidence that one skill is stronger than another: benchmark percentages cannot be compared as if the tests had equal difficulty, scoring rules or task coverage. Compare GPQA with that same benchmark on another model, not with a different test.

Context window and a practical evaluation workload

The 256,000-token window makes multi-document review or a focused repository investigation worth testing. Reserve room for instructions, tool responses and the answer before loading source material. Compare a full-context run with a retrieval-based run on the same questions; the window alone cannot tell you which produces better grounded answers.

36 of the 100 entries have a smaller reported window than Command A. As a planning example, allocating 75% of its reported window to source material gives 192,000 tokens, leaving 64,000 for instructions, conversation, tool messages and output combined. This is arithmetic for a test budget, not an endpoint limit or an assertion that output can use the entire remainder.

Reasoning settings and release comparisons

It is marked non-reasoning by AA. There is no within-model setting spread to quantify, so a claim that a lower budget preserves its score would be unsupported. A derivative should be tested in the actual setting you intend to use.

Other entries credited to Cohere provide a publisher-level comparison, not proof of a shared architecture or training recipe. North Mini Code ranks 66, scores 9.91 and reports 256,000 context tokens; Command A+ ranks 44, scores 13.13 and reports 192,000 context tokens. Compare exact releases and evaluation settings rather than carrying a family’s reputation over to this model.

Nearby ranked alternatives

The closest ranks give a bounded shortlist for evaluating Command A. A small index gap is not a statistical significance claim; compare task outcomes and deployment conditions directly.

How to evaluate an uncensored or abliterated candidate

For Command A, first locate the exact base release and any claimed derivative’s model card. Verify access, redistribution and usage terms at their original sources: AA’s open-weight classification does not assert an open-source license. Record the base revision, derivative revision, runtime and reasoning setting so your comparison can be reproduced.

Weight-based abliteration generally studies differences between activations on refusal-inducing and ordinary prompts, identifies candidate refusal-related directions, and intervenes on model internals. It is not equivalent to changing a system prompt or removing an API filter. Whether a particular intervention is supported depends on the model and implementation; this guide supplies no architecture-specific recipe or claim that the method has been validated on Command A.

Run the base and candidate on the same permitted task set before and after changes. Measure refusal behaviour separately from factual errors, instruction following, coding correctness and tool execution. Use GPQA as one reference for task coverage, while keeping its published percentage separate from your own results. Track any regression and repeat with the exact context length and setting your application needs. A lower refusal rate is not evidence that all other behaviour survived unchanged.

Sources and scope

Snapshot retrieved 2026-10-06T06:17:07.812043+00:00. AA’s Command A model entry supplies the evaluated setting and measurements; the Artificial Analysis leaderboard is the population source. Top 100 distinct active open-weight model names by Artificial Analysis Intelligence Index. Reasoning-budget parentheticals are removed for grouping; the strongest scored setting represents each group. Open weights is AA's classification, not an open-source-license assertion. Scores describe the evaluated base models, not uncensored derivatives. Rank is within this selected active open-weight population, not the complete leaderboard.

For the research behind refusal-direction interventions, see Arditi et al., Refusal in Language Models Is Mediated by a Single Direction. This general research source does not establish successful abliteration of this release. Continue with the abliteration explanation or the current Wild West API line; only the latter lists products for sale.

Questions about Command A