Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

DeepSeek-R1 0528 vs MiniMax M1 80K

DeepSeek · released

Wins 3 of 6 areas

Coding · Reasoning · Facts

MiniMax · released

Wins 3 of 6 areas

Agents · Long documents · Following instructions

The two are evenly matched.DeepSeek-R1 0528 is better at reasoning and facts; MiniMax M1 80K at long documents and following instructions.

Scores updated · 30 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.

Agents 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
MiniMax M1 80K$0.55 to read · $2.20 to write$2.75Price from Artificial Analysis

MiniMax M1 80K costs 37% 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-R1 0528 pulls ahead

  • Hard command-line tasks in a real terminalTerminal-Bench Hard+12.9points aheadDeepSeek-R1 052815.9MiniMax M1 80K3
  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+11.6points aheadDeepSeek-R1 052881.3MiniMax M1 80K69.7
  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.1points aheadDeepSeek-R1 052816.6MiniMax M1 80K8.5

Where MiniMax M1 80K pulls ahead

  • Real work tasks from 44 professionsGDPVal+15.7points aheadMiniMax M1 80K24.7DeepSeek-R1 05289
  • Fixes real GitHub issues in Python projectsSWE-bench Verified+11.4points aheadMiniMax M1 80K56DeepSeek-R1 052844.6
  • Questions about very long textsLongBench v2+9.4points aheadMiniMax M1 80K61.5DeepSeek-R1 052852.1

Every test, side by side

All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingDeepSeek-R1 0528

Full coding ranking

AgentsMiniMax M1 80K
  • GDPValMiniMax M1 80K by 15.7924.7+15.7

Full agents ranking

ReasoningDeepSeek-R1 0528

Full reasoning ranking

FactsDeepSeek-R1 0528

Full facts ranking

Long documentsMiniMax M1 80K

Full long documents ranking

Following instructionsMiniMax M1 80K

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 MiniMax M1 80K?

DeepSeek-R1 0528 and MiniMax M1 80K each win three of the six areas where both have results. DeepSeek-R1 0528 wins coding, reasoning and facts; MiniMax M1 80K wins agents, long documents and following instructions. MiniMax M1 80K costs 37% less.

Which is better for coding?

DeepSeek-R1 0528. It wins 2 of the 3 coding tests both models report; MiniMax M1 80K wins 1.

Which is cheaper?

DeepSeek-R1 0528 costs $1.35 per million input tokens and $3.00 per million output tokens; MiniMax M1 80K costs $0.55 and $2.20. That makes MiniMax M1 80K about 37% cheaper for the same work.

How do you compare the two?

We use the 30 benchmark tests both models have published scores on. The verdict counts the 13 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.