ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Command R+vsGemma 4 26B A4B

Gemma 4 26B A4B leads 1 of 1 shared benchmark. Gemma 4 26B A4B has the larger context window (256K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 1
Gemma 4 26B A4B leads
Cheaper per token
list price, input + output
Larger context
Gemma 4 26B A4B
256K tokens
Provider uptime (30d)
100% · 100%
Cohere · Google
Command R+
Cohere · released 2024-08-30
text
Context
128K
Max out
4K
Input /1M
$2.5
Output /1M
$10
Cached /1M
Scores
1 · 1 core
Gemma 4 26B A4B
Google · released 2026-04-02
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
Quality

Benchmark matrix

BenchmarkCommand R+Gemma 4 26B A4BΔEdge
Reported by both · 1
LMArena Elo1203.7 1434.5 -230.8Gemma 4 26B A4B
Only Command R+ reports · 0
Command R+ reports nothing Gemma 4 26B A4B does not.
Only Gemma 4 26B A4B reports · 5
GPQA Diamondnot reported82.3%
MMLU-Pronot reported82.6%
AIME 2026not reported88.3%
Humanity's Last Exam (no tools)not reported8.7%
LiveCodeBench v6not reported77.1%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Command R+ minus Gemma 4 26B A4B in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecCommand R+Gemma 4 26B A4BEdge
Context window128K tokens256K tokensGemma 4 26B A4B
Max output4K tokens
Input price / 1M$2.5
Output price / 1M$10
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$12.5
Modalitiestexttext · visionGemma 4 26B A4B
Released2024-08-302026-04-02
Cited benchmark scores16
Reliability

Provider status

All providers
More matchups

Command R+ vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Command R+ and Gemma 4 26B A4B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.