Noometry

Model comparison

GPT-6 Luna vs MiniMax-M2.5

GPT-6 Luna is the stronger model overall, scoring 45.1 to 38.1 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and MiniMax-M2.5 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Luna leads 31.7 to 17.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 16.8% for MiniMax-M2.5.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 205K.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaMiniMax-M2.5
ProviderOpenAIMiniMax
Noometry Index45.138.1
Released2026-09-222026-02-12
WeightsProprietaryOpen
Context window1.05M205K
Max output128K131K
Input $ / M tokens$0.10$0.30
Output $ / M tokens$0.50$1.20
Results tracked1833

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-M2.5: 47.9 (#53)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena WebDev15831386
LMArena Coding14481380
DeepSWE66.6%—
FrontierCode42.4%—
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—68.3%
ALE-Bench—618.17

Agentic & Tool Use Not comparable

GPT-6 Luna: —, MiniMax-M2.5: 30.2 (#70)

BenchmarkGPT-6 LunaMiniMax-M2.5
Terminal-Bench—42.7%
Vending-Bench 2—-23.16

Reasoning GPT-6 Luna leads

GPT-6 Luna: 31.7 (#68), MiniMax-M2.5: 17.6 (#281)

BenchmarkGPT-6 LunaMiniMax-M2.5
NYT Connections (extended)68.7%16.8%
LMArena Hard Prompts14151372
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
ARC-AGI-1—63.7%
Epoch Capabilities Index—146.68

Math GPT-6 Luna leads

GPT-6 Luna: 35.6 (#140), MiniMax-M2.5: 25.8 (#242)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Math13961378
ProofBench—4%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 40.1 (#110), MiniMax-M2.5: 38.6 (#132)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Expert14581378
Vectara Hallucination Rate—9.1%

Multimodal Not comparable

GPT-6 Luna: 42.0 (#27), MiniMax-M2.5: —

BenchmarkGPT-6 LunaMiniMax-M2.5
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 51.0 (#111), MiniMax-M2.5: 47.3 (#147)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Non-English13901338
LMArena Chinese14251392
LMArena Russian13921359
LMArena Spanish14161354
LMArena French—1363
LMArena German—1361
LMArena Japanese—1169
LMArena Korean—1232

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.7 (#85), MiniMax-M2.5: 71.7 (#143)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Instruction Following14141353

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.3 (#95), MiniMax-M2.5: 37.4 (#211)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Longer Query14171367
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.4 (#115), MiniMax-M2.5: 54.1 (#149)

BenchmarkGPT-6 LunaMiniMax-M2.5
LMArena Text13921359
LMArena Creative Writing13571331
LMArena Multi-Turn14001364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is GPT-6 Luna better than MiniMax-M2.5?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 38.1 on the Noometry Index.

Which is cheaper, GPT-6 Luna or MiniMax-M2.5?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.

Is GPT-6 Luna or MiniMax-M2.5 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 47.9 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-M2.5 share?

15 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper