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

BenchmarkScoreMetricPercentile
SEA-HELM (English) - MuSR80.64Normalized Score93.3
QIMMA - 3LM HumanEval+79.88pass@1 (%)86.4
SEA-HELM (English) - LiveCodeBench v665.45Normalized Score83.3
SEA-HELM (English) - IFEval91.46Normalized Score78.3
SEA-HELM (English) - MathArena39.6Normalized Score73.3
SEA-HELM (Thai) - Safety56.37Normalized Score73
QIMMA - 3LM MBPP+66.67pass@1 (%)72.2
SEA-HELM (Thai) - Toxicity Detection42.53Normalized Score71.6
SEA-HELM (Tamil) - SEA-Safeguard74.24Normalized Score67.6
SEA-HELM (Indonesian) - SEA-Safeguard71.09Normalized Score66.2
SEA-HELM (Filipino) - Kalahi (LLM Judge)68.99Normalized Score62.2
SEA-HELM (Filipino) - SEA-MT-Bench (LLM Judge)79.46Normalized Score60.8

Interactive version: theaggregate.ai/model?slug=command-a-plus-05-2026-bf16 · How It Works · Data refreshed daily, snapshot 2026-11-22.