RankingMT-AIME 2025 Arabic/Japanese/Korean · source release snapshot; version as labeled

MT-AIME 2025 Arabic/Japanese/Korean · source release snapshot; version as labeled

Data updated 12 Sept 2026

Bucket
Supporting evidence
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

The available records have no admitted matched comparison in the capability core. Raw results remain available below.

Compare published benchmark results with category weights →

Models

ModelScoreHarnessEvidenceSource-recorded date
Command A Plus 05 2026Cohere86%
Reported settings & source

Internal Command A Translate translations; Arabic,Japanese,Korean.

First-party chart numeric label, visually verified.

Command A+ launch benchmarks · Image6 · reviewed 2026-09-06

Command A+ launch benchmarkslab self-report2026-09-06
Command A Reasoning 08 2025Cohere53%
Reported settings & source

Internal Command A Translate translations; Arabic,Japanese,Korean.

First-party chart numeric label, visually verified.

Command A+ launch benchmarks · Image6 · reviewed 2026-09-06

Command A+ launch benchmarkslab self-report2026-09-06