Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

GPT-5.6 Luna vs MiniMax M2.7

31 SHARED BENCHMARKS

Across 31 shared benchmarks, GPT-5.6 Luna scores higher on 29 and MiniMax M2.7 on 2. The widest gap is AA-Omniscience · Non-hallucination, where MiniMax M2.7 scores 64.4 against 7.4. Tracked API pricing per million tokens: GPT-5.6 Luna $0.20 in / $1.20 out, MiniMax M2.7 $0.30 in / $1.20 out.

OPENAIVSMINIMAX31 SHARED29–2 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerOpenAIMiniMax
Released
Price per 1M tokens input / output$0.20 / $1.20$0.30 / $1.20
Cost of 1M in + 1M out$1.40 1.1× less$1.50
Head-to-head of 31 shared benchmarks29 wins2 wins
Scores tracked independently verified201 43 ◆99 5 ◆

Release dates per Artificial Analysis. Prices: OpenAI's own price page for GPT-5.6 Luna; Artificial Analysis for MiniMax M2.7. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaGPT-5.6 LunaWINSMiniMax M2.7
Reasoning30GPT-5.6 Luna leads 3 of 3 · widest: Humanity's Last Exam 39.5 vs 29.6
Coding50GPT-5.6 Luna leads 5 of 5 · widest: Terminal-Bench 2.1 80.9 vs 55.4
Agentic60GPT-5.6 Luna leads 6 of 6 · widest: AA ApexAgents 35.8 vs 10.6
Factuality11Even, 1–1 of 2
Long Context10GPT-5.6 Luna leads 1 of 1 · widest: AA-LCR 83.7 vs 78.3
Math20GPT-5.6 Luna leads 2 of 2 · widest: HMMT Feb. 2026 98.5 vs 71.2

Biggest gaps

GPT-5.6 Luna pulls furthest ahead on

  1. AA ApexAgents35.8 vs 10.6
  2. τ-Bench V3 · Banking31.1 vs 9.9
  3. GDPVal47.2 vs 24.9

MiniMax M2.7 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination64.4 vs 7.4

Every shared benchmark31 · grouped by area

Reasoning 3

Coding 5

Agentic 6

BrowseComp83.354.1
GDPVal47.224.9
Terminal-Bench 4.011.60

Long Context 1

AA-LCR83.778.3

Math 2

Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (openai-official, direct), otherwise the lowest tracked offer.

Compare GPT-5.6 Luna withALL PAIRINGS →

Compare MiniMax M2.7 withALL PAIRINGS →