ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemma 4 26B A4BvsMistral Small 4

Gemma 4 26B A4B leads 2 of 2 shared benchmarks. Both offer a 256K-token context window.

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
Tie
both 256K tokens
Provider uptime (30d)
100% · 100%
Google · Mistral AI
Gemma 4 26B A4B
Google · released 2026-04-02
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
Mistral Small 4
Mistral AI · released 2026-03-16
textvision
Context
256K
Max out
Input /1M
$0.15
Output /1M
$0.6
Cached /1M
$0.015
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkGemma 4 26B A4BMistral Small 4ΔEdge
Reported by both · 2
GPQA Diamond82.3% 71.2% +11.1 ptGemma 4 26B A4B
MMLU-Pro82.6% 78% +4.6 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 Mistral Small 4 reports · 1
Artificial Analysis Long Context Reasoningnot reported0.72
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 Mistral Small 4 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 A4BMistral Small 4Edge
Context window256K tokens256K tokensTie
Max output
Input price / 1M$0.15
Output price / 1M$0.6
Cached input / 1M$0.015
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.75
Modalitiestext · visiontext · visionTie
Released2026-04-022026-03-16
Cited benchmark scores63
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 Mistral Small 4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.