ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemma 4 26B A4BvsLlama 4 Maverick

Gemma 4 26B A4B leads 2 of 2 shared benchmarks. Llama 4 Maverick has the larger context window (1M tokens).

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

Shared benchmarks
2 – 0
Gemma 4 26B A4B leads
Cheaper per token
list price, input + output
Larger context
Llama 4 Maverick
1M tokens
Provider uptime (30d)
100% · —
Google · Meta
Gemma 4 26B A4B
Google · released 2026-04-02
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
Llama 4 Maverick
Meta · released 2025-04-05
textvision
Context
1M
Max out
Input /1M
Output /1M
Cached /1M
Scores
2 · 2 core
Quality

Benchmark matrix

BenchmarkGemma 4 26B A4BLlama 4 MaverickΔEdge
Reported by both · 2
GPQA Diamond82.3% 69.8% +12.5 ptGemma 4 26B A4B
MMLU-Pro82.6% 80.5% +2.1 ptGemma 4 26B A4B
Only Gemma 4 26B A4B reports · 4
AIME 202688.3% not reported
Humanity's Last Exam (no tools)8.7% not reported
LMArena Elo1434.5 not reported
LiveCodeBench v677.1% not reported
Only Llama 4 Maverick reports · 0
Llama 4 Maverick reports nothing Gemma 4 26B A4B does not.
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 Gemma 4 26B A4B minus Llama 4 Maverick 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

SpecGemma 4 26B A4BLlama 4 MaverickEdge
Context window256K tokens1M tokensLlama 4 Maverick
Max output
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
Modalitiestext · visiontext · visionTie
Released2026-04-022025-04-05
Cited benchmark scores62
Reliability

Provider status

All providers
Built by Respan
Which one wins on your data?

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