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.
Unified ELO 1603 ± 48, rank #473 of 1776 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 73.95 | Accuracy (%) | 91.6 |
| LLM Stats (MathVista) | 80.6 | Score (%) | 86.5 |
| AA Omniscience | -3.98 | Score | 83.7 |
| LLM Stats (WMT24++) | 81 | Score (%) | 72.7 |
| AA TAU-2 Bench | 80.7 | Accuracy (%) | 70.9 |
| AA Humanity's Last Exam | 11.35 | Accuracy (%) | 66.1 |
| AA Terminal-Bench Hard | 25 | Accuracy (%) | 66 |
| AA SciCode | 37.85 | Accuracy (%) | 65 |
| Artificial Analysis Intelligence Index | 22.51 | Intelligence Index | 64.8 |
| AA GPQA Diamond | 76.06 | Accuracy (%) | 64 |
| LLM Stats (CharXiv-D) | 88 | Score (%) | 60 |
| AA CritPt | 0.29 | Accuracy (%) | 58.7 |
Interactive version: theaggregate.ai/model?slug=command-a-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.