ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Ministral 3 3BvsMistral Small 4

Mistral Small 4 leads 1 of 1 shared benchmark. Ministral 3 3B is 3.8x cheaper per token. Both offer a 256K-token context window.

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

Shared benchmarks
0 – 1
Mistral Small 4 leads
Cheaper per token
Ministral 3 3B
3.8x cheaper, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
100%
Mistral AI
Ministral 3 3B
Mistral AI · released 2025-12-02
textvision
Context
256K
Max out
Input /1M
$0.1
Output /1M
$0.1
Cached /1M
$0.01
Scores
3 · 2 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

BenchmarkMinistral 3 3BMistral Small 4ΔEdge
Reported by both · 1
GPQA Diamond53.4% 71.2% -17.8 ptMistral Small 4
Only Ministral 3 3B reports · 2
AIME 202572.1% not reported
LiveCodeBench54.8% not reported
Only Mistral Small 4 reports · 2
MMLU-Pronot reported78%
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 Ministral 3 3B 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

SpecMinistral 3 3BMistral Small 4Edge
Context window256K tokens256K tokensTie
Max output
Input price / 1M$0.1 $0.15 Ministral 3 3B
Output price / 1M$0.1 $0.6 Ministral 3 3B
Cached input / 1M$0.01 $0.015 Ministral 3 3B
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.2$0.75Ministral 3 3B
Modalitiestext · visiontext · visionTie
Released2025-12-022026-03-16
Cited benchmark scores33
Reliability

Mistral AI status

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

Public benchmarks are a starting point. Run Ministral 3 3B and Mistral Small 4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.