Noometry

Model comparison

DeepSeek V4 Flash vs MiniMax-M2.7

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.7 on the Noometry Index.

Last verified . 25 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 25 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and MiniMax-M2.7 in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4 Flash leads 60.3 to 25.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4 Flash and 24.7% for MiniMax-M2.7.
  • DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
  • DeepSeek V4 Flash accepts more context: 1M tokens versus 205K.

Side by side

DeepSeek V4 FlashMiniMax-M2.7
ProviderDeepSeekMiniMax
Noometry Index53.637.7
Released2026-04-242026-03-18
WeightsOpenOpen
Context window1M205K
Max output393K131K
Input $ / M tokens$0.15$0.30
Output $ / M tokens$0.60$1.20
Results tracked4130

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), MiniMax-M2.7: 41.8 (#120)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena WebDev15821398
SciCode49.9%47%
WeirdML63%37%
LMArena Coding14571454
ALE-Bench1,306599.25
FrontierCode18.8%—

Agentic & Tool Use Not comparable

DeepSeek V4 Flash: —, MiniMax-M2.7: 25.1 (#111)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
Terminal-Bench—45.1%
ExploitBench—13.3%
GBAEval—0%

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), MiniMax-M2.7: 19.7 (#253)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
NYT Connections (extended)89.6%24.7%
CritPt16.6%0.6%
LMArena Hard Prompts14441422
Epoch Capabilities Index154.49145.85
ARC-AGI-261.4%—
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—
ARC-AGI-189%—
Chess Puzzles33%—
Thematic Generalization—39.3%
Mystery Game Puzzles34%—
DTBench90.9%—
LMCA41.7%—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), MiniMax-M2.7: 25.9 (#263)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
ProofBench56%3%
LMArena Math14271420
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
OTIS Mock AIME 2024-202594.4%—

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), MiniMax-M2.7: 37.7 (#152)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena Expert14411444
GPQA Diamond91%—
SimpleQA Verified33.6%—
Vectara Hallucination Rate—12.9%

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), MiniMax-M2.7: 50.3 (#123)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena Non-English14201382
LMArena Chinese14681441
LMArena French14391421
LMArena German14181398
LMArena Japanese14061262
LMArena Korean13841313
LMArena Russian14281383
LMArena Spanish14361403

Instruction Following Too close to call

DeepSeek V4 Flash: 74.9 (#81), MiniMax-M2.7: 74.1 (#103)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena Instruction Following14211405

Long Context Too close to call

DeepSeek V4 Flash: 43.8 (#85), MiniMax-M2.7: 43.3 (#99)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena Longer Query14341419

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), MiniMax-M2.7: 58.9 (#112)

BenchmarkDeepSeek V4 FlashMiniMax-M2.7
LMArena Text14321405
LMArena Creative Writing14031354
LMArena Multi-Turn14491412
EQ-Bench Creative Writing1559—

Frequently asked questions

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

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.7 on the Noometry Index.

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

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

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

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

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

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

25 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper