Noometry

Model comparison

GPT-5.4 mini vs MiniMax-M2.7

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 3.2× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and MiniMax-M2.7 in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 mini leads 45.5 to 25.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 24.7% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
  • GPT-5.4 mini accepts more context: 400K tokens versus 205K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniMiniMax-M2.7
ProviderOpenAIMiniMax
Noometry Index45.037.7
Released2026-03-172026-03-18
WeightsProprietaryOpen
Context window400K205K
Max output128K131K
Input $ / M tokens$0.75$0.30
Output $ / M tokens$4.50$1.20
Results tracked4630

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), MiniMax-M2.7: 41.8 (#120)

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena WebDev13971398
SciCode49.9%47%
WeirdML60.3%37%
LMArena Coding14381454
ALE-Bench1,189599.25
FrontierCode27%—

Agentic & Tool Use GPT-5.4 mini leads

GPT-5.4 mini: 29.9 (#81), MiniMax-M2.7: 25.1 (#111)

BenchmarkGPT-5.4 miniMiniMax-M2.7
Terminal-Bench—45.1%
DeepResearch Bench36.3%—
ExploitBench—13.3%
GBAEval—0%

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), MiniMax-M2.7: 19.7 (#253)

BenchmarkGPT-5.4 miniMiniMax-M2.7
NYT Connections (extended)61.8%24.7%
CritPt10%0.6%
Thematic Generalization61.7%39.3%
LMArena Hard Prompts14241422
Epoch Capabilities Index148.84145.85
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
ARC-AGI-163.7%—
Chess Puzzles24%—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), MiniMax-M2.7: 25.9 (#263)

BenchmarkGPT-5.4 miniMiniMax-M2.7
ProofBench21%3%
LMArena Math14191420
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), MiniMax-M2.7: 37.7 (#152)

BenchmarkGPT-5.4 miniMiniMax-M2.7
Vectara Hallucination Rate5.5%12.9%
LMArena Expert14351444
GPQA Diamond86.9%—
SimpleQA Verified29.4%—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), MiniMax-M2.7: —

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), MiniMax-M2.7: 50.3 (#123)

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena Non-English14051382
LMArena Chinese14461441
LMArena French14401421
LMArena German14091398
LMArena Japanese13741262
LMArena Korean13681313
LMArena Russian14171383
LMArena Spanish14051403

Instruction Following Too close to call

GPT-5.4 mini: 74.1 (#102), MiniMax-M2.7: 74.1 (#103)

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena Instruction Following14051405

Long Context Too close to call

GPT-5.4 mini: 43.0 (#112), MiniMax-M2.7: 43.3 (#99)

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena Longer Query14071419

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), MiniMax-M2.7: 58.9 (#112)

BenchmarkGPT-5.4 miniMiniMax-M2.7
LMArena Text14121405
LMArena Creative Writing13701354
LMArena Multi-Turn14291412
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than MiniMax-M2.7?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 3.2× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Which is cheaper, GPT-5.4 mini 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; GPT-5.4 mini lists at $0.75 and $4.50.

Is GPT-5.4 mini or MiniMax-M2.7 better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 205K.

How many benchmarks do GPT-5.4 mini and MiniMax-M2.7 share?

27 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper