language benchmark
MT-AIME 2025
MT-AIME 2025 is Cohere's internal multilingual translation of AIME 2025, evaluated for Arabic, Japanese, and Korean in the Command A+ release.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MT-AIME 2025 Ranking
Higher score ranks better on this benchmark.
| 1 | CO | 86.0% | 100.0% | 1 | C |
MT-AIME 2025 Highlights
The leading models and scores on this benchmark.
What is MT-AIME 2025?
What MT-AIME 2025 measures and how its scores work.
MT-AIME 2025 is Cohere's internal multilingual translation of AIME 2025, evaluated for Arabic, Japanese, and Korean in the Command A+ release.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MT-AIME 2025
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mt-aime-2025|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MT-AIME 2025.
Which model scores highest on MT-AIME 2025?
Command A+ is currently ranked first with 86.0%.
What does MT-AIME 2025 measure?
MT-AIME 2025 is Cohere's internal multilingual translation of AIME 2025, evaluated for Arabic, Japanese, and Korean in the Command A+ release.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.