Noometry

Model comparison

DeepSeek-V3.1 vs MiniMax-M2.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 38.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

MiniMax-M2.1 MiniMax

38.4

Rank #177 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 27.3 to 15.8.
  • 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 Index42.238.4
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: 39.8 (#140), MiniMax-M2.1: 40.1 (#132)

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: 27.7 (#91)

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

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), MiniMax-M2.1: 15.8 (#301)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Hard Prompts14171410
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: 36.1 (#125), MiniMax-M2.1: 35.6 (#142)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Math14201396

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), MiniMax-M2.1: 37.7 (#143)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
Vectara Hallucination Rate5.5%11.8%
LMArena Expert14031432

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), MiniMax-M2.1: 50.2 (#123)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Non-English14001378
LMArena Chinese14701430
LMArena French14471405
LMArena German14121380
LMArena Japanese13741287
LMArena Korean13371297
LMArena Russian14051386
LMArena Spanish14291396

Instruction Following Too close to call

DeepSeek-V3.1: 74.1 (#105), MiniMax-M2.1: 74.0 (#108)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Instruction Following14001399

Long Context MiniMax-M2.1 leads

DeepSeek-V3.1: 36.3 (#227), MiniMax-M2.1: 43.2 (#98)

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

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), MiniMax-M2.1: 58.5 (#114)

BenchmarkDeepSeek-V3.1MiniMax-M2.1
LMArena Text14201392
LMArena Creative Writing14011362
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 42.2 to 38.4 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 (39.8 vs 40.1); 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