ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemma 4 12B UnifiedvsMinistral 3 14B

Gemma 4 12B Unified leads 1 of 1 shared benchmark. Both offer a 256K-token context window.

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

Shared benchmarks
1 – 0
Gemma 4 12B Unified leads
Cheaper per token
list price, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
100% · 100%
Google · Mistral AI
Gemma 4 12B Unified
Google · released 2026-06-03
textvisionaudio
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
5 · 4 core
Ministral 3 14B
Mistral AI · released 2025-12-02
textvision
Context
256K
Max out
Input /1M
$0.2
Output /1M
$0.2
Cached /1M
$0.02
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkGemma 4 12B UnifiedMinistral 3 14BΔEdge
Reported by both · 1
GPQA Diamond78.8% 71.2% +7.6 ptGemma 4 12B Unified
Only Gemma 4 12B Unified reports · 4
MMLU-Pro77.2% not reported
AIME 202677.5% not reported
Humanity's Last Exam (no tools)5.2% not reported
LiveCodeBench v672% not reported
Only Ministral 3 14B reports · 2
AIME 2025not reported85%
LiveCodeBenchnot reported64.6%
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 12B Unified minus Ministral 3 14B 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 12B UnifiedMinistral 3 14BEdge
Context window256K tokens256K tokensTie
Max output
Input price / 1M$0.2
Output price / 1M$0.2
Cached input / 1M$0.02
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.4
Modalitiestext · vision · audiotext · visionGemma 4 12B Unified
Released2026-06-032025-12-02
Cited benchmark scores53
Reliability

Provider status

All providers
More matchups

Gemma 4 12B Unified vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemma 4 12B Unified and Ministral 3 14B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.