Noometry

Model comparison

GPT-5.6 Luna vs MiniMax-M2.7

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 37.7 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-5.6 Luna scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 25.9.
  • The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 3% for MiniMax-M2.7.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
  • GPT-5.6 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-5.6 LunaMiniMax-M2.7
ProviderOpenAIMiniMax
Noometry Index54.637.7
Released2026-07-092026-03-18
WeightsProprietaryOpen
Context window1.05M205K
Max output128K131K
Input $ / M tokens$0.20$0.30
Output $ / M tokens$1.20$1.20
Results tracked5230

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-M2.7: 41.8 (#120)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena WebDev15191398
SciCode53.6%47%
WeirdML60.9%37%
LMArena Coding14661454
ALE-Bench1,667599.25
DeepSWE67.2%—
FrontierCode39.8%—
CursorBench35.9%—

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 34.4 (#45), MiniMax-M2.7: 25.1 (#111)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
Terminal-Bench—45.1%
APEX-Agents43%—
BALROG45.6%—
ExploitBench—13.3%
GBAEval—0%
GDP.pdf22.7%—
Vending-Bench 24,095—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.6 (#43), MiniMax-M2.7: 19.7 (#253)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
NYT Connections (extended)69.4%24.7%
CritPt20.6%0.6%
LMArena Hard Prompts14511422
Epoch Capabilities Index156.39145.85
ARC-AGI-259.5%—
SimpleBench46.8%—
Kagi LLM Benchmark49.1%—
ARC-AGI-188%—
Chess Puzzles40%—
Thematic Generalization—39.3%
Mystery Game Puzzles21%—
DTBench89.1%—
LMCA48.5%—
Surface Evolver Bench61.9%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.7 (#14), MiniMax-M2.7: 25.9 (#263)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
ProofBench60%3%
LMArena Math14581420
FrontierMath (Tiers 1-3)82.1%—
FrontierMath Tier 461%—
OTIS Mock AIME 2024-202598.3%—

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.5 (#34), MiniMax-M2.7: 37.7 (#152)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Expert14781444
GPQA Diamond91.6%—
SimpleQA Verified41%—
Vectara Hallucination Rate—12.9%

Multimodal Not comparable

GPT-5.6 Luna: 42.7 (#28), MiniMax-M2.7: —

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Vision1258—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual GPT-5.6 Luna leads

GPT-5.6 Luna: 52.8 (#78), MiniMax-M2.7: 50.3 (#123)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Non-English14171382
LMArena Chinese14701441
LMArena French14561421
LMArena German14541398
LMArena Japanese14111262
LMArena Korean14151313
LMArena Russian14281383
LMArena Spanish14481403

Instruction Following GPT-5.6 Luna leads

GPT-5.6 Luna: 75.6 (#57), MiniMax-M2.7: 74.1 (#103)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Instruction Following14371405

Long Context Too close to call

GPT-5.6 Luna: 43.9 (#82), MiniMax-M2.7: 43.3 (#99)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Longer Query14361419

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.0 (#29), MiniMax-M2.7: 58.9 (#112)

BenchmarkGPT-5.6 LunaMiniMax-M2.7
LMArena Text14311405
LMArena Creative Writing13961354
LMArena Multi-Turn14341412
EQ-Bench Creative Writing1829—
EQ-Bench 41156—

Frequently asked questions

Is GPT-5.6 Luna better than MiniMax-M2.7?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 37.7 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or MiniMax-M2.7?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

Is GPT-5.6 Luna or MiniMax-M2.7 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 205K.

How many benchmarks do GPT-5.6 Luna and MiniMax-M2.7 share?

25 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper