Noometry

Model comparison

DeepSeek-V3.1 vs MiniMax-M2.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

MiniMax-M2.1 MiniMax

38.9

Rank #178 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 6 categories and MiniMax-M2.1 in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 16.6.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for DeepSeek-V3.1 and 11.8% for MiniMax-M2.1.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
  • MiniMax-M2.1 accepts more context: 205K tokens versus 164K.

Side by side

DeepSeek-V3.1MiniMax-M2.1
ProviderDeepSeekMiniMax
Noometry Index42.838.9
Released2025-08-212025-12-23
WeightsOpenOpen
Context window164K205K
Max output8K131K
Input $ / M tokens$0.25$0.30
Output $ / M tokens$0.95$1.20
Results tracked2722

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

DeepSeek-V3.1: 40.3 (#144), MiniMax-M2.1: 40.4 (#143)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Coding14171421
LMArena WebDev—1384
WeirdML38.4%—
ALE-Bench—623.83

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, MiniMax-M2.1: 27.9 (#98)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
Terminal-Bench—36.6%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), MiniMax-M2.1: 16.6 (#302)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Hard Prompts14171411
SimpleBench40%—
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—11.2%
DTBench82.7%—
LMCA24.3%—
Epoch Capabilities Index139.92—
ForecastBench58—

Math Too close to call

DeepSeek-V3.1: 38.9 (#122), MiniMax-M2.1: 38.3 (#138)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Math14201397

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), MiniMax-M2.1: 38.3 (#147)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
Vectara Hallucination Rate5.5%11.8%
LMArena Expert14051431

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.6 (#106), MiniMax-M2.1: 50.0 (#128)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Non-English14001378
LMArena Chinese14691430
LMArena French14471404
LMArena German14111381
LMArena Japanese13781287
LMArena Korean13371298
LMArena Russian14051387
LMArena Spanish14311397

Instruction Following Too close to call

DeepSeek-V3.1: 73.9 (#110), MiniMax-M2.1: 73.8 (#112)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Instruction Following14001400

Long Context MiniMax-M2.1 leads

DeepSeek-V3.1: 36.3 (#232), MiniMax-M2.1: 43.2 (#101)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Longer Query14221416
Fiction.LiveBench52.8%—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), MiniMax-M2.1: 58.3 (#120)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Text14201392
LMArena Creative Writing14011361
LMArena Multi-Turn14081396
EQ-Bench Creative Writing1436—

Frequently asked questions

Is DeepSeek-V3.1 better than MiniMax-M2.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.9 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or MiniMax-M2.1?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

Is DeepSeek-V3.1 or MiniMax-M2.1 better for coding?

They score almost the same on coding (40.3 vs 40.4); test both on your own repository before choosing.

Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and MiniMax-M2.1 share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and MiniMax-M2.1 has 22.

Related comparisons

Go deeper