Home  /  Compare  /  Command A+ vs Gemma 4 31B
Head to head

Command A+ vs Gemma 4 31B.

Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.

VS
Google DeepMind

Verdict by category

CategoryCommand A+Gemma 4 31BWinner
League Score0.013.4Gemma 4 31B
Coding (SWE-bench %)51.0——
Reasoning (GPQA %)—84.3—
Context (tokens)128000262144Gemma 4 31B
Speed (tok/s)———

Tale of the tape

SpecCommand A+Gemma 4 31B
MakerCohereGoogle DeepMind
ReleasedMay 20, 2026Apr 2, 2026
League Score013
Context128,000 tokens262,144 tokens
Max output64,000—
$/1M input——
$/1M output——
WeightsOpenOpen
Speed——

Head-to-head benchmarks (shared only)

BenchmarkCommand A+Gemma 4 31B
No shared benchmark measurements yet — shown as not measured, never interpolated.

Cost at three workloads

WorkloadCommand A+Gemma 4 31B
Light — 1M in / 250K out——
Standard — 10M in / 2.5M out——
Long-context — 50M in / 5M out——

The pick

Pick Command A+ if coding is the priority.

Pick Gemma 4 31B if you want the higher overall League Score; you need the bigger context window.

All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.

Frequently asked questions

Which is better overall, Command A+ or Gemma 4 31B?

Gemma 4 31B leads on overall League Score, 13 to 0 — a gap of 13 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.

Which has the bigger context window, Command A+ or Gemma 4 31B?

Gemma 4 31B, with 262.1K of context against 128K for Command A+.

Are Command A+ and Gemma 4 31B open source?

Command A+ is open weights — it can be downloaded and self-hosted; Gemma 4 31B is open weights — it can be downloaded and self-hosted.