Home  /  Compare  /  Gemini 3.1 Pro Preview vs Inkling 2 Mini
Head to head

Gemini 3.1 Pro Preview vs Inkling 2 Mini.

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

Google DeepMind
VS
Thinking Machines Lab

Verdict by category

CategoryGemini 3.1 Pro PreviewInkling 2 MiniWinner
League Score60.760.1Gemini 3.1 Pro Preview
Coding (SWE-bench %)75.679.2Inkling 2 Mini
Reasoning (GPQA %)94.386.6Gemini 3.1 Pro Preview
Context (tokens)10000001000000Draw
Speed (tok/s)———

Tale of the tape

SpecGemini 3.1 Pro PreviewInkling 2 Mini
MakerGoogle DeepMindThinking Machines Lab
ReleasedFeb 19, 2026Nov 20, 2026
League Score6160
Context1,000,000 tokens1,000,000 tokens
Max output65,536—
$/1M input$2.00—
$/1M output$12.00—
WeightsClosedOpen
Speed——

Head-to-head benchmarks (shared only)

BenchmarkGemini 3.1 Pro PreviewInkling 2 Mini
GPQA Diamond94.386.6
SWE-bench Verified75.679.2

Cost at three workloads

WorkloadGemini 3.1 Pro PreviewInkling 2 Mini
Light — 1M in / 250K out$5.00—
Standard — 10M in / 2.5M out$50.00—
Long-context — 50M in / 5M out$160.00—

The pick

Pick Gemini 3.1 Pro Preview if you want the higher overall League Score.

Pick Inkling 2 Mini if you want downloadable weights / self-hosting; coding is the priority.

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, Gemini 3.1 Pro Preview or Inkling 2 Mini?

On overall League Score they are effectively tied — Gemini 3.1 Pro Preview scores 61 and Inkling 2 Mini scores 60. The category verdicts on this page are where the real differences live.

Which is cheaper, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Only Gemini 3.1 Pro Preview has published API pricing in our database ($4.50 blended per 1M tokens); Inkling 2 Mini has no tracked API price, so a like-for-like cost verdict is not possible.

Which has the bigger context window, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Neither — both take 1M of context.

Which is better for coding, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Inkling 2 Mini scores higher on SWE-bench Verified, 79.2% vs 75.6% of real GitHub issues resolved.

Which is better at reasoning, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Gemini 3.1 Pro Preview leads on GPQA Diamond, 94.3% vs 86.6% on graduate-level science questions.

Are Gemini 3.1 Pro Preview and Inkling 2 Mini open source?

Gemini 3.1 Pro Preview is closed weights — API access only; Inkling 2 Mini is open weights — it can be downloaded and self-hosted.