Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Inkling 2 Mini vs Kimi K3

Thinking Machines · released

Wins 0 of 5 areas

—

Moonshot · released

Wins 4 of 5 areas

Coding · Agents · Images and charts · Long documents

Kimi K3 is the stronger all-rounder.Inkling 2 Mini is cheaper.

Scores updated · 23 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.

Coding, 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.

Inkling 2 Mini$0.15 to read · $0.50 to write$0.65Price from Artificial Analysis
Kimi K3$3.00 to read · $15.00 to write$18Price from Artificial Analysis

Inkling 2 Mini costs 96% 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 Kimi K3 pulls ahead

  • Command-line tasks in a real terminalTerminal-Bench 2.1+13.4points aheadKimi K385Inkling 2 Mini71.6
  • Finds hard-to-locate facts by browsing the webBrowseComp+12.2points aheadKimi K391.2Inkling 2 Mini79
  • Abstract visual puzzles that people can solveARC-AGI-2+11.1points aheadKimi K360.4Inkling 2 Mini49.3

Where Inkling 2 Mini pulls ahead

  • Research-level physics problemsCritPt+8points aheadInkling 2 Mini31.4Kimi K323.4

Every test, side by side

All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingKimi K3

Full coding ranking

AgentsKimi K3

Full agents ranking

ReasoningEven

Full reasoning ranking

Images and chartsKimi K3

Full images and charts ranking

Long documentsKimi K3

Full long documents ranking

Other results16 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.

  • ZeroBenchKimi K3 by 241741+24
  • CritPt v2 HardKimi K3 by 23.51740.5+23.5
  • GDPval-AA 2.1Kimi K3 by 224 rating points13191543+224 rating
  • DeepSWE 1.1Kimi K3 by 20.848.269+20.8
  • HLE-DiamondKimi K3 by 11.715.226.9+11.7
  • SWEBench Pro v2 (Hard)Kimi K3 by 10.377.988.2+10.3
  • ARC-AGI-1Kimi K3 by 1084.594.5+10
  • DeepSearchQA (F1)Kimi K3 by 9.785.395+9.7
  • Vals Finance IndexKimi K3 by 7.950.158+7.9
  • Terminal-Bench 4.0Kimi K3 by 75.612.6+7
  • GDP (Surge AI)Kimi K3 by 5.216.822+5.2
  • Chartography originalKimi K3 by 4.522.126.6+4.5
  • JobBenchKimi K3 by 3.349.652.9+3.3
  • ScreenSpot Pro originalInkling 2 Mini by 2.776.573.8+2.7
  • OmniDocBenchInkling 2 Mini by 1.792.891.1+1.7
  • ScreenSpot-Pro (No tools)Inkling 2 Mini by 1.687.786.1+1.6

Questions people ask

Which is better, Inkling 2 Mini or Kimi K3?

Kimi K3 wins four of the five areas where both have results: coding, agents, images and charts and long documents. Inkling 2 Mini wins none, but costs 96% less. They are level on reasoning.

Which is better for coding?

Kimi K3. It wins the one coding test both models report.

Which is cheaper?

Inkling 2 Mini costs $0.15 per million input tokens and $0.50 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Inkling 2 Mini about 96% cheaper for the same work.

How do you compare the two?

We use the 23 benchmark tests both models have published scores on. The verdict counts the 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.