RankingAIME 2025 · source release snapshot; version as labeled
AIME 2025 · source release snapshot; version as labeled
- Bucket
- Hard reasoning
- Unit
- percent
- Direction
- Higher is better
- Version
- source release snapshot; version as labeled
- Display harness
- Command A+ launch benchmarks
- Board
- https://cohere.com/blog/command-a-plus
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| Command A Plus 05 2026Cohere | 90%Reported settings & sourceOfficial30questions x10 repeats; pass@1. First-party chart numeric label, visually verified. Command A+ launch benchmarks · Image3 · reviewed 2026-09-06 | Command A+ launch benchmarks | lab self-report | 2026-09-06 |
| Command A Reasoning 08 2025Cohere | 57%Reported settings & sourceOfficial30questions x10 repeats; pass@1. First-party chart numeric label, visually verified. Command A+ launch benchmarks · Image3 · reviewed 2026-09-06 | Command A+ launch benchmarks | lab self-report | 2026-09-06 |