Noometry

Model comparison

GPT-6 Luna vs MiniMax-M2.7

GPT-6 Luna is the stronger model overall, scoring 45.1 to 37.4 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 6 categories and MiniMax-M2.7 in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-6 Luna leads 54.7 to 41.4.
  • The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 24.7% for MiniMax-M2.7.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 205K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaMiniMax-M2.7
ProviderOpenAIMiniMax
Noometry Index45.137.4
Released2026-09-222026-03-18
WeightsProprietaryOpen
Context window1.05M205K
Max output128K131K
Input $ / M tokens$0.10$0.30
Output $ / M tokens$0.50$1.20
Results tracked1830

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 54.7 (#24), MiniMax-M2.7: 41.4 (#115)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena WebDev15831397
LMArena Coding14481454
DeepSWE66.6%—
FrontierCode42.4%—
SciCode—47%
WeirdML—37%
ALE-Bench—599.25

Agentic & Tool Use Not comparable

GPT-6 Luna: —, MiniMax-M2.7: 24.9 (#103)

BenchmarkGPT-6 LunaMiniMax-M2.7
Terminal-Bench—45.1%
ExploitBench—13.3%
GBAEval—0%

Reasoning GPT-6 Luna leads

GPT-6 Luna: 31.7 (#68), MiniMax-M2.7: 19.0 (#248)

BenchmarkGPT-6 LunaMiniMax-M2.7
NYT Connections (extended)68.7%24.7%
LMArena Hard Prompts14151422
CritPt—0.6%
Thematic Generalization—39.3%
Epoch Capabilities Index—145.84

Math GPT-6 Luna leads

GPT-6 Luna: 35.6 (#140), MiniMax-M2.7: 24.9 (#254)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Math13961420
ProofBench—3%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 40.1 (#110), MiniMax-M2.7: 37.1 (#151)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Expert14581443
Vectara Hallucination Rate—12.9%

Multimodal Not comparable

GPT-6 Luna: 42.0 (#27), MiniMax-M2.7: —

BenchmarkGPT-6 LunaMiniMax-M2.7
Furniture Assembly44.2%—

Multilingual Too close to call

GPT-6 Luna: 51.0 (#111), MiniMax-M2.7: 50.5 (#120)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Non-English13901382
LMArena Chinese14251439
LMArena Russian13921383
LMArena Spanish14161403
LMArena French—1422
LMArena German—1398
LMArena Japanese—1261
LMArena Korean—1313

Instruction Following Too close to call

GPT-6 Luna: 74.7 (#85), MiniMax-M2.7: 74.2 (#101)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Instruction Following14141404

Long Context Too close to call

GPT-6 Luna: 43.3 (#95), MiniMax-M2.7: 43.3 (#94)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Longer Query14171419

Writing & Preference Too close to call

GPT-6 Luna: 58.4 (#115), MiniMax-M2.7: 59.1 (#107)

BenchmarkGPT-6 LunaMiniMax-M2.7
LMArena Text13921404
LMArena Creative Writing13571354
LMArena Multi-Turn14001413

Frequently asked questions

Is GPT-6 Luna better than MiniMax-M2.7?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 37.4 on the Noometry Index.

Which is cheaper, GPT-6 Luna or MiniMax-M2.7?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

Is GPT-6 Luna or MiniMax-M2.7 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 205K.

How many benchmarks do GPT-6 Luna and MiniMax-M2.7 share?

15 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper