Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014

DeepSeek-V3.2 vs Kimi K2.5

DeepSeek · released

Wins 0 of 7 areas

—

Moonshot · released

Wins 7 of 7 areas

Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions

Kimi K2.5 is the stronger all-rounder.DeepSeek-V3.2 is cheaper.

Scores updated · 64 tests both models report · How we compare

Where each one wins

Tests won in each of the seven 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.

Following instructions rests on a single test.

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.

DeepSeek-V3.2$0.28 to read · $0.42 to write$0.70Price from Artificial Analysis
Kimi K2.5$0.60 to read · $3.00 to write$3.60Price from Artificial Analysis

DeepSeek-V3.2 costs 81% less for the same work.

The biggest differences

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

Where Kimi K2.5 pulls ahead

  • Long, multi-file coding tasks in real codebasesSWE-bench Pro+35.1points aheadKimi K2.550.7DeepSeek-V3.215.6
  • Finds hard-to-locate facts by browsing the webBrowseComp+23.5points aheadKimi K2.574.9DeepSeek-V3.251.4
  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+17points aheadKimi K2.534.3DeepSeek-V3.217.3

Where DeepSeek-V3.2 pulls ahead

  • Customer-service tasks in a simulated bankτ-Bench V3 · Banking+4.6points aheadDeepSeek-V3.218.8Kimi K2.514.2
  • Long professional tasks in banking, consulting and lawAA ApexAgents+3points aheadDeepSeek-V3.214.5Kimi K2.511.5
  • Command-line tasks in a real terminalTerminal-Bench 2.1+1.1points aheadDeepSeek-V3.246.8Kimi K2.545.7

Every test, side by side

All 64 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingKimi K2.5

Full coding ranking

AgentsKimi K2.5

Full agents ranking

ReasoningKimi K2.5

Full reasoning ranking

FactsKimi K2.5

Full facts ranking

MathKimi K2.5

Full math ranking

Long documentsKimi K2.5

Full long documents ranking

Following instructionsKimi K2.5
  • IFBenchKimi K2.5 by 9.560.770.2+9.5

Full following instructions ranking

Other results37 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.

Questions people ask

Which is better, DeepSeek-V3.2 or Kimi K2.5?

Kimi K2.5 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. DeepSeek-V3.2 wins none, but costs 81% less.

Which is better for coding?

Kimi K2.5. It wins 6 of the 8 coding tests both models report; DeepSeek-V3.2 wins 1, and 1 is a tie.

Which is cheaper?

DeepSeek-V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; Kimi K2.5 costs $0.60 and $3.00. That makes DeepSeek-V3.2 about 81% cheaper for the same work.

How do you compare the two?

We use the 64 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 37 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.

Compare DeepSeek-V3.2 with

DeepSeek

Across the field

Compare Kimi K2.5 with

Moonshot

Across the field

All comparisons