Command A+: benchmark results
Cohere's first Apache 2.0 open frontier MoE (218B total, 25B active), unifying the Command A line. Provider: Cohere. Released 2026-05-20. Access: Open.
Aggregate Rating 1608 ± 18, rank #413 of 1656 rated models, from 115 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Hallucination Rate | 14.16 | Hallucination Rate (%) | 99.5 |
| MLCR-AA - Conciseness | 99.44 | Conciseness (%) | 95.8 |
| AA IFBench | 73.95 | Accuracy (%) | 91.6 |
| LLM Stats (MathVista) | 80.6 | Score (%) | 84.2 |
| AA-Omniscience Index - Law | -0.6 | Omniscience Index | 80.3 |
| AA-Omniscience Index - Business | -3.2 | Omniscience Index | 77.1 |
| AA-Omniscience Index - Health | -10.4 | Omniscience Index | 77 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | -6 | Omniscience Index | 76.8 |
| AA-Omniscience Index - Humanities & Social Sciences | -1.5 | Omniscience Index | 75 |
| AA Omniscience | -4.02 | Score | 72.9 |
| Tau2-Bench Telecom | 80.7 | Success Rate (%) | 71.7 |
| AA TAU-2 Bench | 80.7 | Accuracy (%) | 71 |
Interactive version: theaggregate.ai/model?slug=command-a-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.