command-a-plus-05-2026-bf16: benchmark results
Provider: Cohere. Released 2026-05-20. Access: Open.
Aggregate Rating 1594 ± 34, rank #981 of 10524 rated models, from 147 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (English) - MuSR | 80.64 | Normalized Score | 93.3 |
| QIMMA - 3LM HumanEval+ | 79.88 | pass@1 (%) | 86.4 |
| SEA-HELM (English) - LiveCodeBench v6 | 65.45 | Normalized Score | 83.3 |
| SEA-HELM (English) - IFEval | 91.46 | Normalized Score | 78.3 |
| SEA-HELM (English) - MathArena | 39.6 | Normalized Score | 73.3 |
| SEA-HELM (Thai) - Safety | 56.37 | Normalized Score | 73 |
| QIMMA - 3LM MBPP+ | 66.67 | pass@1 (%) | 72.2 |
| SEA-HELM (Thai) - Toxicity Detection | 42.53 | Normalized Score | 71.6 |
| SEA-HELM (Tamil) - SEA-Safeguard | 74.24 | Normalized Score | 67.6 |
| SEA-HELM (Indonesian) - SEA-Safeguard | 71.09 | Normalized Score | 66.2 |
| SEA-HELM (Filipino) - Kalahi (LLM Judge) | 68.99 | Normalized Score | 62.2 |
| SEA-HELM (Filipino) - SEA-MT-Bench (LLM Judge) | 79.46 | Normalized Score | 60.8 |
Interactive version: theaggregate.ai/model?slug=command-a-plus-05-2026-bf16 · How It Works · Data refreshed daily, snapshot 2026-11-22.