Noometry

Model comparison

GPT-6 Luna vs MiniMax-M3

GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 16 benchmarks with published results for both. GPT-6 Luna scores higher in 3 categories and MiniMax-M3 in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 40.1.
  • The biggest single-benchmark swing is FrontierCode: 42.4% for GPT-6 Luna and 14.7% for MiniMax-M3.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaMiniMax-M3
ProviderOpenAIMiniMax
Noometry Index45.143.5
Released2026-09-222026-06-01
WeightsProprietaryOpen
Context window1.05M1M
Max output128K512K
Input $ / M tokens$0.10$0.30
Output $ / M tokens$0.50$1.20
Results tracked1841

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-M3: 41.5 (#111)

BenchmarkGPT-6 LunaMiniMax-M3
FrontierCode42.4%14.7%
LMArena WebDev15831482
LMArena Coding14481470
DeepSWE66.6%—
SciCode—47.1%
ALE-Bench—640.02

Agentic & Tool Use Not comparable

GPT-6 Luna: —, MiniMax-M3: 22.5 (#121)

BenchmarkGPT-6 LunaMiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning GPT-6 Luna leads

GPT-6 Luna: 31.7 (#68), MiniMax-M3: 29.3 (#83)

BenchmarkGPT-6 LunaMiniMax-M3
NYT Connections (extended)68.7%65.1%
LMArena Hard Prompts14151447
SimpleBench—45.8%
CritPt—3.7%
Chess Puzzles—14%
Mystery Game Puzzles—8%
DTBench—78.9%
LMCA—33.7%
Surface Evolver Bench—55%
Epoch Capabilities Index—147
ForecastBench—61.4

Math MiniMax-M3 leads

GPT-6 Luna: 35.6 (#140), MiniMax-M3: 39.1 (#83)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Math13961432
OTIS Mock AIME 2024-2025—71.1%
ProofBench—18%

Knowledge MiniMax-M3 leads

GPT-6 Luna: 40.1 (#110), MiniMax-M3: 58.4 (#32)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Expert14581462
GPQA Diamond—90.9%

Multimodal GPT-6 Luna leads

GPT-6 Luna: 42.0 (#27), MiniMax-M3: 39.5 (#45)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Vision—1254
Furniture Assembly44.2%—
LMArena Document—1435

Multilingual MiniMax-M3 leads

GPT-6 Luna: 51.0 (#111), MiniMax-M3: 53.2 (#70)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Non-English13901420
LMArena Chinese14251465
LMArena Russian13921430
LMArena Spanish14161431
LMArena French—1445
LMArena German—1424
LMArena Japanese—1381
LMArena Korean—1372

Instruction Following Too close to call

GPT-6 Luna: 74.7 (#85), MiniMax-M3: 75.7 (#56)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Instruction Following14141433

Long Context Too close to call

GPT-6 Luna: 43.3 (#95), MiniMax-M3: 44.2 (#68)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Longer Query14171445

Writing & Preference MiniMax-M3 leads

GPT-6 Luna: 58.4 (#115), MiniMax-M3: 62.3 (#79)

BenchmarkGPT-6 LunaMiniMax-M3
LMArena Text13921433
LMArena Creative Writing13571405
LMArena Multi-Turn14001441
EQ-Bench 4—1150

Frequently asked questions

Is GPT-6 Luna better than MiniMax-M3?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.5 on the Noometry Index.

Which is cheaper, GPT-6 Luna or MiniMax-M3?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

Is GPT-6 Luna or MiniMax-M3 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 41.5 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 1M.

How many benchmarks do GPT-6 Luna and MiniMax-M3 share?

16 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper