The Open-Source AI Stack
RSS
All models

Models · Compare

Command A vs Gemini 2.5 Pro

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Command A B: Gemini 2.5 Pro
Released 2025-03-132025-03-25
Developer CohereGoogle DeepMind
Openness Open weightsProprietary
License CC-BY-NC-4.0Proprietary
OSI-approved nono
Data released nono
Training code nono
Architecture denseunknown
Total params 111B
Active params
Experts
Context window 256K1.0M
Attention unknownunknown
Position enc. unknownunknown
Pretraining tokens
Post-training sft, rlhfrlhf
Training hardware
$/M input $2.50$1.25
$/M output $10.00$10.00
Output tok/sec 44.8127.3

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 71.2 2026-05-21 86.2 2026-05-21
GPQA-Diamond 52.7 2026-05-21

Code

LiveCodeBench 28.7 2026-05-21 80.1 2026-05-21

Math

MATH 81.9 2026-05-21 96.7 2026-05-21
AIME 2024 9.7 2026-05-21
AIME 2025 13.0 2026-05-21 87.7 2026-05-21

Held-out / arena

Context · A

Cohere's most-performant model at release, replacing Command R+ as the enterprise flagship. 111B parameters, 256K context, 23-language support, and 150 percent throughput vs Command R+ on two A100s or H100s. Released March 13 2025.

Context · B

The first Gemini release to clearly lead on LMArena Elo and on hard reasoning benchmarks. Native 1M-token context with reported 2M expansion in pipeline.

Command A detail → · Gemini 2.5 Pro detail →