CohereCommand R
Command R is a Cohere open-weights model, released 12 Mar 2024. Its best configuration ranks #718 of 785 on the BenchLeader Index at 38.2 ±9.8, in the lower half. The ± is the point: 349 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (39) and lowest in knowledge (5). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 12 Mar 2024
- Overall index38
- Reasoning39
- Coding39
- Maths36
- Knowledge5
- Human preference39
- Composite35
Versions
Cohere has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Command R 08 2024 | 30 Aug 2024 | – | – |
| Command Rthis page | 12 Mar 2024 | 38.2 | #718 |
How its index has moved
9 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1257#290 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 28.4%#531 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.8%#473 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1281#285 | Arena (LMArena) |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1207#291 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LegalBench | 33.0%#143 | Vals AI |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1236#289 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1251#289 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1209#287 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1213#291 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1264#284 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 5.0#607 | Artificial Analysis |
See also
Questions people ask
- What are Command R's benchmark scores?
- As of 25 Oct 2026, Command R scores 38.2 ±9.8 on the BenchLeader Index, strongest in human preference (39) and weakest in knowledge (5). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does Command R rank?
- Command R is #718 of 785 ranked configurations on 25 Oct 2026. 349 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Command R released?
- Cohere released Command R on 12 Mar 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Command R: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/command-r.