Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models738Deals30d266Policy30d65, 16 pendingSources1,010

DeepSeek-R1 0528 vs DeepSeek-V3.1

DeepSeek · released

Wins 2 of 6 areas

Reasoning · Facts

DeepSeek · released

Wins 3 of 6 areas

Coding · Long documents · Following instructions

DeepSeek-V3.1 wins more areas, narrowly.DeepSeek-R1 0528 is better at reasoning.

Scores updated · 32 tests both models report · How we compare

Where each one wins

Tests won in each of the six 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.

Long documents 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-R1 0528$1.35 to read · $3.00 to write$4.35Price from Artificial Analysis
DeepSeek-V3.1$0.56 to read · $1.68 to write$2.24Price from Artificial Analysis

DeepSeek-V3.1 costs 49% less for the same work.

The biggest differences

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

Where DeepSeek-V3.1 pulls ahead

  • Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+24points aheadDeepSeek-V3.154.5DeepSeek-R1 052830.5
  • Fixes real GitHub issues in Python projectsSWE-bench Verified+21.4points aheadDeepSeek-V3.166DeepSeek-R1 052844.6
  • Finds hard-to-locate facts by browsing the webBrowseComp+21.1points aheadDeepSeek-V3.130DeepSeek-R1 05288.9

Where DeepSeek-R1 0528 pulls ahead

  • Real work tasks from 44 professionsGDPVal+3.4points aheadDeepSeek-R1 05289DeepSeek-V3.15.6
  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.4points aheadDeepSeek-R1 052881.3DeepSeek-V3.177.9
  • Very hard expert questions across many subjectsHumanity's Last Exam+1.5points aheadDeepSeek-R1 052815.8DeepSeek-V3.114.3

Every test, side by side

All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-V3.1

Full coding ranking

AgentsEven

Full agents ranking

ReasoningDeepSeek-R1 0528

Full reasoning ranking

FactsDeepSeek-R1 0528

Full facts ranking

Long documentsDeepSeek-V3.1
  • AA-LCRDeepSeek-V3.1 by 155.756.7+1

Full long documents ranking

Following instructionsDeepSeek-V3.1

Full following instructions ranking

Other results17 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-R1 0528 or DeepSeek-V3.1?

DeepSeek-V3.1 wins three of the six areas where both have results: coding, long documents and following instructions. DeepSeek-R1 0528 wins reasoning and facts. They are level on agents.

Which is better for coding?

DeepSeek-V3.1. It wins 3 of the 4 coding tests both models report; DeepSeek-R1 0528 wins 1.

Which is cheaper?

DeepSeek-R1 0528 costs $1.35 per million input tokens and $3.00 per million output tokens; DeepSeek-V3.1 costs $0.56 and $1.68. That makes DeepSeek-V3.1 about 49% cheaper for the same work.

How do you compare the two?

We use the 32 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.