Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

GPT-5.1 vs GPT-5.6 Luna

29 SHARED BENCHMARKS

Across 29 shared benchmarks, GPT-5.1 scores higher on 4 and GPT-5.6 Luna on 25. The widest gap is AA-Omniscience · Non-hallucination, where GPT-5.1 scores 48.1 against 7.4. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $1.25 per million input tokens).

OPENAIVSOPENAI29 SHARED4–25 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerOpenAIOpenAI
Released
Price per 1M tokens input / output$1.25 / $10.00$0.20 / $1.20
Cost of 1M in + 1M out$11.25$1.40 8.0× less
Head-to-head of 29 shared benchmarks4 wins25 wins
Scores tracked independently verified105 41 ◆201 43 ◆

Release dates per Artificial Analysis. Prices: Artificial Analysis for GPT-5.1; Artificial Analysis for GPT-5.6 Luna. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaGPT-5.1WINSGPT-5.6 Luna
Reasoning14GPT-5.6 Luna leads 4 of 5 · widest: CritPt 4.9 vs 20.6
Coding04GPT-5.6 Luna leads 4 of 4 · widest: Terminal-Bench 2.1 52.4 vs 80.9
Agentic03GPT-5.6 Luna leads 3 of 3 · widest: GDPVal 15.6 vs 47.2
Factuality21GPT-5.1 leads 2 of 3 · widest: AA-Omniscience · Non-hallucination 48.1 vs 7.4
Long Context01GPT-5.6 Luna leads 1 of 1 · widest: AA-LCR 80 vs 83.7
Multimodal02GPT-5.6 Luna leads 2 of 2 · widest: MMMU-Pro 75.5 vs 78.6

Biggest gaps

GPT-5.1 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination48.1 vs 7.4
  2. SimpleQA Verified48 vs 41
  3. SimpleBench53.2 vs 46.8

GPT-5.6 Luna pulls furthest ahead on

  1. CritPt20.6 vs 4.9
  2. ARC-AGI-259.6 vs 17.6
  3. GDPVal47.2 vs 15.6

Every shared benchmark29 · grouped by area

Reasoning 5

BenchmarkGPT-5.1MARGINGPT-5.6 Luna
ARC-AGI-217.6 ◆◆ 59.6
CritPt4.920.6
GPQA Diamond87.391.1
SimpleBench53.2 ◆◆ 46.8

Coding 4

BenchmarkGPT-5.1MARGINGPT-5.6 Luna
LMArena · WebDev1394 ◆◆ 1520
SciCode43.353.6

Agentic 3

BenchmarkGPT-5.1MARGINGPT-5.6 Luna
BrowseComp50.883.3
GDPVal15.647.2

Long Context 1

BenchmarkGPT-5.1MARGINGPT-5.6 Luna
AA-LCR8083.7

Multimodal 2

BenchmarkGPT-5.1MARGINGPT-5.6 Luna
LMArena · Vision1250 ◆◆ 1259
MMMU-Pro75.578.6

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 (direct, direct), otherwise the lowest tracked offer.

Compare GPT-5.1 withALL PAIRINGS →

Compare GPT-5.6 Luna withALL PAIRINGS →