ExamenosCommand A+
Explore Command A+ from Cohere: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.
Compare Command A+ with other models →Compare subscription plansExplore data coverage
Pricing · OpenRouter
Dated cached OpenRouter rates in USD per 1M tokens. Open the dashboard for live enhancements. Per-metric endpoint minima can refer to different providers; they are not a guaranteed combined rate from one endpoint.
| Tier | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Date & source |
|---|---|---|---|---|---|
| Default | $0.3 | $1.5 | $0.15 | — | 2026-11-01 · OpenRouter source |
Recorded pricing notes
OpenRouter list rate captured 1 November 2026, pending the next min-healthy refresh. No contributor sibling. OpenRouter canonical cohere/command-a-plus-05-2026.
Official / vendor benchmarks
Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| τ²-bench (Telecom) | 85%unknown effort | All 1 recorded result & sources85% · raw 85 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: standard τ²-bench settings and user simulation (Barres et al. 2025). Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| Terminal-Bench Hard (Cohere, Terminus-2) | 25%unknown effort | All 1 recorded result & sources25% · raw 25 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Terminus-2, following the Artificial Analysis methodology. Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| IFBench | 74%unknown effort | All 1 recorded result & sources74% · raw 74 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: IFBench single turn, loose mode, prompt accuracy over 1470 samples of 294 prompts × 5. Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| AIME 2025 (Cohere, 30 questions × 10) | 90%unknown effort | All 1 recorded result & sources90% · raw 90 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere repeat protocol, 30 questions × 10, pass@1. Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| SciCode | 38%unknown effort | All 1 recorded result & sources38% · raw 38 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: 65 test problems with 288 subproblems, scientist-annotated background, following the Artificial Analysis methodology. Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| CharXiv (descriptive) | 88%unknown effort | All 1 recorded result & sources88% · raw 88 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere vendor run. Cohere launch figure, read visually on 1 November 2026; rounded chart label. Evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| MMMU | 75.1%unknown effort | All 1 recorded result & sources75.1% · raw 75.1 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere vendor run. Value stated in Cohere launch prose; tool setting and evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| MathVista | 80.6%unknown effort | All 1 recorded result & sources80.6% · raw 80.6 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere vendor run. Value stated in Cohere launch prose; tool setting and evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| CharXiv (reasoning) | 52.7%unknown effort | All 1 recorded result & sources52.7% · raw 52.7 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere vendor run. Value stated in Cohere launch prose; tool setting and evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| MMMU Pro (no tools) | 63%unknown effort | All 1 recorded result & sources63% · raw 63 % Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Harness: Cohere vendor run. Value stated in Cohere launch prose; tool setting and evaluation date unpublished. https://cohere.com/blog/command-a-plus |
| AA Intelligence Index (vendor-cited, version unstated) | 37unknown effort | All 1 recorded result & sources37 · raw 37 index Headline · unknown effort · Own vendor Source/record date: 2026-05-20 Cohere cites an Artificial Analysis Intelligence Index score of 37 at launch; index version unstated. Vendor-cited, not a direct Artificial Analysis observation. The current AA page reads 6 on v5.0, stored separately in evaluator data. https://cohere.com/blog/command-a-plus |
Independent evaluators
Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| DataAnalyticsBench · questions correct /43 · Plotly DataAnalyticsBench | 18 correctunknown effort | All 1 recorded result & sources18 correct · raw 18 correct Headline · unknown effort · Independent evaluator Source/record date: 2026-11-01 Harness: Plotly Studio Embedded, one run on 43 private English data-analytics questions in a synthetic wind-energy warehouse. Claude Sonnet 5 judges against Plotly answer key. One or two questions can be noise; no error bars. Exact checkpoint hash, run date and effort unpublished. Company-operated analytics benchmark, distinct from provider results. Plotly deep dive https://plotly.com/blog/cohere-command-a-plus-plotly-data-analytics-bench/ on 30 October. https://plotly.com/blog/introducing-dataanalyticsbench/ |
| Intelligence Index v5.0 · Artificial Analysis | 6unknown effort | All 1 recorded result & sources6 · raw 6 index Headline · unknown effort · Independent evaluator Source/record date: 2026-11-01 AA model page for Command A+; Cohere’s launch figure of 37 cites an earlier unstated index version and stays in official rows. Manual observation of Artificial Analysis’s public model page, 1 November 2026. AA’s displayed rounding; no API, download, hidden precision or inferred run date. https://artificialanalysis.ai/models/command-a-plus |
Read how we select and source scores or the comparison guide.