Noometry

Model comparison

GPT-5.6 Luna vs MiniMax-M3

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index.

Last verified . 38 shared benchmarks.

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 38 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and MiniMax-M3 in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 40.0.
  • The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 18% for MiniMax-M3.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 LunaMiniMax-M3
ProviderOpenAIMiniMax
Noometry Index54.643.8
Released2026-07-092026-06-01
WeightsProprietaryOpen
Context window1.05M1M
Max output128K512K
Input $ / M tokens$0.20$0.30
Output $ / M tokens$1.20$1.20
Results tracked5241

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

Category by category

Coding GPT-5.6 Luna leads

GPT-5.6 Luna: 54.5 (#28), MiniMax-M3: 41.8 (#118)

BenchmarkGPT-5.6 LunaMiniMax-M3
FrontierCode39.8%14.7%
LMArena WebDev15191482
SciCode53.6%47.1%
LMArena Coding14661469
ALE-Bench1,667640.02
DeepSWE67.2%—
CursorBench35.9%—
WeirdML60.9%—

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 34.4 (#45), MiniMax-M3: 22.6 (#130)

BenchmarkGPT-5.6 LunaMiniMax-M3
APEX-Agents43%37.7%
Vending-Bench 24,0952,158
OSWorld 2.0—4.6%
BALROG45.6%—
GBAEval—0.9%
GDP.pdf22.7%—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.6 (#43), MiniMax-M3: 30.1 (#87)

BenchmarkGPT-5.6 LunaMiniMax-M3
SimpleBench46.8%45.8%
NYT Connections (extended)69.4%65.1%
CritPt20.6%3.7%
Chess Puzzles40%14%
LMArena Hard Prompts14511447
Mystery Game Puzzles21%8%
DTBench89.1%78.9%
LMCA48.5%33.7%
Surface Evolver Bench61.9%55%
Epoch Capabilities Index156.39146.95
ARC-AGI-259.5%—
Kagi LLM Benchmark49.1%—
ARC-AGI-188%—
ForecastBench—61.4

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.7 (#14), MiniMax-M3: 40.0 (#95)

BenchmarkGPT-5.6 LunaMiniMax-M3
OTIS Mock AIME 2024-202598.3%71.1%
ProofBench60%18%
LMArena Math14581429
FrontierMath (Tiers 1-3)82.1%—
FrontierMath Tier 461%—

Knowledge Too close to call

GPT-5.6 Luna: 58.5 (#34), MiniMax-M3: 58.4 (#35)

BenchmarkGPT-5.6 LunaMiniMax-M3
GPQA Diamond91.6%90.9%
LMArena Expert14781461
SimpleQA Verified41%—

Multimodal GPT-5.6 Luna leads

GPT-5.6 Luna: 42.7 (#28), MiniMax-M3: 40.2 (#51)

BenchmarkGPT-5.6 LunaMiniMax-M3
LMArena Vision12581253
LMArena Document14571435
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—

Multilingual Too close to call

GPT-5.6 Luna: 52.8 (#78), MiniMax-M3: 53.0 (#75)

BenchmarkGPT-5.6 LunaMiniMax-M3
LMArena Non-English14171420
LMArena Chinese14701463
LMArena French14561447
LMArena German14541426
LMArena Japanese14111381
LMArena Korean14151372
LMArena Russian14281428
LMArena Spanish14481432

Instruction Following Too close to call

GPT-5.6 Luna: 75.6 (#57), MiniMax-M3: 75.5 (#62)

BenchmarkGPT-5.6 LunaMiniMax-M3
LMArena Instruction Following14371433

Long Context Too close to call

GPT-5.6 Luna: 43.9 (#82), MiniMax-M3: 44.2 (#72)

BenchmarkGPT-5.6 LunaMiniMax-M3
LMArena Longer Query14361445

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.0 (#29), MiniMax-M3: 62.1 (#83)

BenchmarkGPT-5.6 LunaMiniMax-M3
LMArena Text14311433
LMArena Creative Writing13961404
EQ-Bench 411561150
LMArena Multi-Turn14341442
EQ-Bench Creative Writing1829—

Frequently asked questions

Is GPT-5.6 Luna better than MiniMax-M3?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 43.8 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or MiniMax-M3?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

Is GPT-5.6 Luna or MiniMax-M3 better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 1M.

How many benchmarks do GPT-5.6 Luna and MiniMax-M3 share?

38 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper