Benchmark Almanac

Command A+

Command A+.

Cohere Released May 20th, 2026 Compare with others
18
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Cohere May 2026

Command A+

Open weights

140.2 #177 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • MMMU-Pro 63% #63 /90
  • IFBench 74% #28 /80
  • SciCode 38% #34 /49

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
IFBench 74% #28 of 80 Lab model card
Last Translation Benchmark 1.43 #27 of 36 Official leaderboard
SEA-HELM 56.7 #54 of 71 Official leaderboard
WMT24++ 81% #13 of 15 Lab model card
MT-AIME (Cohere internal) 86% #1 of 1 Lab model card

Math and science

BenchmarkScoreRankSource
AIME 2025 90% #50 of 143 Lab model card

Coding

BenchmarkScoreRankSource
SciCode 38% #34 of 49 Lab model card

Agents and tools

BenchmarkScoreRankSource
tau2-bench 85% #26 of 79 Lab model card
Terminal-Bench Hard 25% #7 of 13 Lab model card

Professional work

BenchmarkScoreRankSource
LegalBench 61.4% #129 of 138 Official leaderboard
MedScribe 55.7% #93 of 97 Official leaderboard
MedCode 19.7% #96 of 96 Official leaderboard
Vals Finance Agent v2 9.04% #80 of 80 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
MathVista 80.6% #29 of 70 Lab model card
MMMU 75.1% #43 of 103 Lab model card
MMMU-Pro 63% #63 of 90 Lab model card
CharXiv 52.7% #69 of 75 Lab model card

Other

BenchmarkScoreRankSource
Artificial Analysis Intelligence Index v4.0 37.0 #5 of 5 Lab model card

Its lab's numbers put it at 140.2, number 177 of 404

The Self-Reported Index fits one score to the 10 capability results Cohere reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 136.6 to 143.7. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Introducing Command A+: Making sovereign agentic capabilities available to all (Cohere blog) May 20, 2026