CohereCommand R+
Command R+ is a Cohere open-weights model, released 30 Aug 2024. Its best configuration ranks #771 of 785 on the BenchLeader Index at 34.3 ±9.0, in the lower half. The ± is the point: 216 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 (42) and lowest in knowledge (12). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 30 Aug 2024
- Overall index34
- Reasoning30
- Coding19
- Maths39
- Knowledge12
- Human preference42
- Composite35
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 |
|---|---|---|---|
| SimpleBench | 17.4%#86 | SimpleBench | |
| Arena Hard Prompts | 1261#287 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 32.3%#510 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.6%#484 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 31.1%#128 | Vals AI | |
| LMCAnot in index | 5.0%#190 | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 54.9%#197 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1280#286 | Arena (LMArena) | |
| LiveCodeBench | 18.2%#135 | Vals AI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1232#277 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLU-Pro | 44.0%#129 | Vals AI | |
| LegalBench | 68.3%#125 | Vals AI | |
| MedQA | 2.6%#91 | Vals AI | |
| MMLUnot in index | 69.4%#56 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1254#277 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1276#274 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1263#254 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1250#277 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1282#269 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 119.2#178 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 5.3#586 | Artificial Analysis |
See also
Questions people ask
- What are Command R+'s benchmark scores?
- As of 25 Oct 2026, Command R+ scores 34.3 ±9.0 on the BenchLeader Index, strongest in human preference (42) and weakest in knowledge (12). That rests on 10 independent benchmark results, and every score on this page links to its publisher.
- How does Command R+ rank?
- Command R+ is #771 of 785 ranked configurations on 25 Oct 2026. 216 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 30 Aug 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-plus.