Home  /  Compare  /  Gemma 4 31B vs Mistral Large 4
Head to head

Gemma 4 31B vs Mistral Large 4.

Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.

Google DeepMind
VS
Mistral AI

Verdict by category

CategoryGemma 4 31BMistral Large 4Winner
League Score14.514.6Mistral Large 4
Coding (SWE-bench %)———
Reasoning (GPQA %)84.3——
Context (tokens)2621441000000Mistral Large 4
Speed (tok/s)———

Tale of the tape

SpecGemma 4 31BMistral Large 4
MakerGoogle DeepMindMistral AI
ReleasedApr 2, 2026Oct 6, 2026
League Score1415
Context262,144 tokens1,000,000 tokens
Max output——
$/1M input—$0.68
$/1M output—$2.09
WeightsOpenClosed
Speed——

Head-to-head benchmarks (shared only)

BenchmarkGemma 4 31BMistral Large 4
LiveBench overall41.547.7

Cost at three workloads

WorkloadGemma 4 31BMistral Large 4
Light — 1M in / 250K out—$1.20
Standard — 10M in / 2.5M out—$12.03
Long-context — 50M in / 5M out—$44.45

The pick

Pick Gemma 4 31B if you want downloadable weights / self-hosting.

Pick Mistral Large 4 if you want the higher overall League Score; you need the bigger context window.

All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.

Frequently asked questions

Which is better overall, Gemma 4 31B or Mistral Large 4?

On overall League Score they are effectively tied — Gemma 4 31B scores 14 and Mistral Large 4 scores 15. The category verdicts on this page are where the real differences live.

Which is cheaper, Gemma 4 31B or Mistral Large 4?

Only Mistral Large 4 has published API pricing in our database ($1.03 blended per 1M tokens); Gemma 4 31B has no tracked API price, so a like-for-like cost verdict is not possible.

Which has the bigger context window, Gemma 4 31B or Mistral Large 4?

Mistral Large 4, with 1M of context against 262.1K for Gemma 4 31B.

Are Gemma 4 31B and Mistral Large 4 open source?

Gemma 4 31B is open weights — it can be downloaded and self-hosted; Mistral Large 4 is closed weights — API access only.