Noometry

Model comparison

DeepSeek V4 Pro vs MiniMax-M2.7

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.4 on the Noometry Index.

Last verified . 26 shared benchmarks.

DeepSeek V4 Pro DeepSeek

54.2

Rank #28 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 26 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 24.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 91.3% for DeepSeek V4 Pro and 24.7% for MiniMax-M2.7.
  • Both cost about the same: $0.43 input and $0.87 output per million tokens.
  • DeepSeek V4 Pro accepts more context: 1M tokens versus 205K.

Side by side

DeepSeek V4 ProMiniMax-M2.7
ProviderDeepSeekMiniMax
Noometry Index54.237.4
Released2026-04-242026-03-18
WeightsOpenOpen
Context window1M205K
Max output393K131K
Input $ / M tokens$0.43$0.30
Output $ / M tokens$0.87$1.20
Results tracked4830

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

Category by category

Coding DeepSeek V4 Pro leads

DeepSeek V4 Pro: 52.2 (#31), MiniMax-M2.7: 41.4 (#115)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
LMArena WebDev15821397
SciCode51%47%
WeirdML66.2%37%
LMArena Coding14701454
ALE-Bench1,403599.25
SWE-bench Verified77.6%—
FrontierCode28.6%—

Agentic & Tool Use DeepSeek V4 Pro leads

DeepSeek V4 Pro: 32.7 (#54), MiniMax-M2.7: 24.9 (#103)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
Terminal-Bench—45.1%
APEX-Agents47.3%—
ExploitBench—13.3%
GBAEval—0%
Vending-Bench 23,285—

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.4 (#22), MiniMax-M2.7: 19.0 (#248)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
NYT Connections (extended)91.3%24.7%
CritPt18%0.6%
LMArena Hard Prompts14611422
Epoch Capabilities Index155.39145.84
ARC-AGI-261.3%—
Kagi LLM Benchmark53.5%—
ARC-AGI-190.5%—
Chess Puzzles47%—
Thematic Generalization—39.3%
Mystery Game Puzzles43%—
DTBench93.9%—
LMCA45.5%—
Surface Evolver Bench40%—
ForecastBench56.1—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.6 (#24), MiniMax-M2.7: 24.9 (#254)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
ProofBench50%3%
LMArena Math14551420
FrontierMath (Tiers 1-3)64.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.6%—
OTIS Mock AIME 2024-202598.6%—

Knowledge DeepSeek V4 Pro leads

DeepSeek V4 Pro: 59.5 (#28), MiniMax-M2.7: 37.1 (#151)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
Vectara Hallucination Rate8.6%12.9%
LMArena Expert14631443
GPQA Diamond91.7%—
SimpleQA Verified52.9%—

Multilingual DeepSeek V4 Pro leads

DeepSeek V4 Pro: 54.5 (#44), MiniMax-M2.7: 50.5 (#120)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
LMArena Non-English14381382
LMArena Chinese14861439
LMArena French14731422
LMArena German14581398
LMArena Japanese14481261
LMArena Korean14521313
LMArena Russian14521383
LMArena Spanish14571403

Instruction Following DeepSeek V4 Pro leads

DeepSeek V4 Pro: 76.3 (#44), MiniMax-M2.7: 74.2 (#101)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
LMArena Instruction Following14481404

Long Context DeepSeek V4 Pro leads

DeepSeek V4 Pro: 45.0 (#49), MiniMax-M2.7: 43.3 (#94)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
LMArena Longer Query14591419
CL-bench Life13.5%—

Writing & Preference DeepSeek V4 Pro leads

DeepSeek V4 Pro: 65.6 (#45), MiniMax-M2.7: 59.1 (#107)

BenchmarkDeepSeek V4 ProMiniMax-M2.7
LMArena Text14511404
LMArena Creative Writing14461354
LMArena Multi-Turn14671413
EQ-Bench Creative Writing1553—
EQ-Bench 41166—

Frequently asked questions

Is DeepSeek V4 Pro better than MiniMax-M2.7?

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.4 on the Noometry Index.

Which is cheaper, DeepSeek V4 Pro or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; DeepSeek V4 Pro lists at $0.43 and $0.87.

Is DeepSeek V4 Pro or MiniMax-M2.7 better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 205K.

How many benchmarks do DeepSeek V4 Pro and MiniMax-M2.7 share?

26 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper