Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Gemma 4 31B vs Inkling 2 Mini

Google · released

Wins 0 of 5 areas

—

Thinking Machines · released

Wins 5 of 5 areas

Coding · Agents · Reasoning · Images and charts · Long documents

Inkling 2 Mini is the stronger all-rounder.Gemma 4 31B is cheaper.

Scores updated · 29 tests both models report · How we compare

Where each one wins

Tests won in each of the five areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

Reasoning, images and charts and long documents rest on a single test each.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

Gemma 4 31B$0.15 to read · $0.40 to write$0.55Price from Artificial Analysis
Inkling 2 Mini$0.15 to read · $0.50 to write$0.65Price from Artificial Analysis

Gemma 4 31B costs 15% less for the same work.

The biggest differences

The tests each model wins by the widest margin, up to three each. Scores are out of 100.

Where Inkling 2 Mini pulls ahead

  • Finds hard-to-locate facts by browsing the webBrowseComp+42points aheadInkling 2 Mini79Gemma 4 31B37
  • Fixes real GitHub issues in Python projectsSWE-bench Verified+33.1points aheadInkling 2 Mini79.2Gemma 4 31B46.1
  • Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+30.7points aheadInkling 2 Mini73.7Gemma 4 31B43

Where Gemma 4 31B pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingInkling 2 Mini

Full coding ranking

AgentsInkling 2 Mini

Full agents ranking

ReasoningInkling 2 Mini
  • CritPtInkling 2 Mini by 301.431.4+30

Full reasoning ranking

Images and chartsInkling 2 Mini
  • MMMU-ProInkling 2 Mini by 1.573.474.9+1.5

Full images and charts ranking

Long documentsInkling 2 Mini

Full long documents ranking

Other results21 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

  • ScreenSpot Pro originalInkling 2 Mini by 70.65.976.5+70.6
  • GDPval-AA 2.1Inkling 2 Mini by 692 rating points6271319+692 rating
  • SWEBench Pro v2 (Hard)Inkling 2 Mini by 63.714.277.9+63.7
  • Vals IndexInkling 2 Mini by 46.5046.5+46.5
  • JobBenchInkling 2 Mini by 41.48.249.6+41.4
  • AutomationBench-AA v1.0.6Inkling 2 Mini by 36.94.941.8+36.9
  • DeepSearchQA (F1)Inkling 2 Mini by 23.661.785.3+23.6
  • ZeroBench (main) with PythonInkling 2 Mini by 221234+22
  • BVBInkling 2 Mini by 21.44768.4+21.4
  • Misbehavior (Internal) ↓Gemma 4 31B by 17.827.69.8+17.8
  • Covert misbehavior (Internal) ↓Gemma 4 31B by 1624.38.3+16
  • CritPt v2 HardInkling 2 Mini by 13417+13
  • GDP (Surge AI)Inkling 2 Mini by 10.8616.8+10.8
  • OmniDocBench v1.6Inkling 2 Mini by 10.382.592.8+10.3
  • Chartography originalInkling 2 Mini by 10.11222.1+10.1
  • HLE-DiamondInkling 2 Mini by 87.215.2+8
  • ZeroBench (main) originalInkling 2 Mini by 8917+8
  • Terminal-Bench 4.0Inkling 2 Mini by 5.605.6+5.6
  • ComplexConstraints v1.1Inkling 2 Mini by 1.831.633.4+1.8
  • MMMU Pro Standard 10Inkling 2 Mini by 1.573.474.9+1.5
  • StrongREJECT (none)tie98.197.8tie

Questions people ask

Which is better, Gemma 4 31B or Inkling 2 Mini?

Inkling 2 Mini wins all five areas where both have results: coding, agents, reasoning, images and charts and long documents. Gemma 4 31B wins none, but costs 15% less.

Which is better for coding?

Inkling 2 Mini. It wins 3 of the 3 coding tests both models report; Gemma 4 31B wins none.

Which is cheaper?

Gemma 4 31B costs $0.15 per million input tokens and $0.40 per million output tokens; Inkling 2 Mini costs $0.15 and $0.50. That makes Gemma 4 31B about 15% cheaper for the same work.

How do you compare the two?

We use the 29 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.