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 1552 ± 1, rank #426 of 1392 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 73.95 | Accuracy (%) | 91.6 |
| LLM Stats (MathVista) | 80.6 | Score (%) | 86.5 |
| CritPt | 30 | Accuracy (self-reported) | 80.8 |
| AA Omniscience | -4.02 | Score | 78 |
| AA TAU-2 Bench | 80.7 | Accuracy (%) | 71 |
| AA Terminal-Bench Hard | 25 | Accuracy (%) | 66 |
| LLM Stats (CharXiv-D) | 88 | Score (%) | 62.5 |
| LLM Stats (WMT24++) | 81 | Score (%) | 61.5 |
| AA Humanity's Last Exam | 11.96 | Accuracy (%) | 60.2 |
| BenchmarkList ECI | 118.87 | Capability Index (ECI) | 60.2 |
| Artificial Analysis Intelligence Index | 15.6 | Intelligence Index | 59.6 |
| AA GPQA Diamond | 76.06 | Accuracy (%) | 58.8 |
Interactive version: theaggregate.ai/model?slug=command-a-plus · How It Works · Data refreshed daily, snapshot 2026-09-05.