Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

GPT-5 vs GPT-5.6 Luna

34 SHARED BENCHMARKS

Across 34 shared benchmarks, GPT-5 scores higher on 8 and GPT-5.6 Luna on 26. The widest gap is ARC-AGI-2, where GPT-5.6 Luna scores 59.6 against 9.9. GPT-5.6 Luna is the cheaper of the two on tracked API pricing ($0.20 against $1.25 per million input tokens).

OPENAIVSOPENAI34 SHARED8–26 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 34 shared benchmarks8 wins26 wins
Scores tracked independently verified210 53 ◆201 43 ◆

Release dates per Artificial Analysis. Prices: Artificial Analysis for GPT-5; Artificial Analysis for GPT-5.6 Luna. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaGPT-5WINSGPT-5.6 Luna
Reasoning14GPT-5.6 Luna leads 4 of 5 · widest: ARC-AGI-2 9.9 vs 59.6
Coding05GPT-5.6 Luna leads 5 of 5 · widest: Terminal-Bench 2.1 35.2 vs 80.9
Agentic03GPT-5.6 Luna leads 3 of 3 · widest: GDPVal 20.3 vs 47.2
Factuality21GPT-5 leads 2 of 3 · widest: AA-Omniscience · Non-hallucination 17.8 vs 7.4
Long Context01GPT-5.6 Luna leads 1 of 1 · widest: AA-LCR 78.2 vs 83.7
Math02GPT-5.6 Luna leads 2 of 2 · widest: FrontierMath Tier 4 21.9 vs 58.5
Multimodal03GPT-5.6 Luna leads 3 of 3 · widest: MMMU-Pro 74.2 vs 78.6

Biggest gaps

GPT-5 pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination17.8 vs 7.4
  2. SimpleQA Verified50.1 vs 41
  3. SimpleBench56.7 vs 46.8

GPT-5.6 Luna pulls furthest ahead on

  1. ARC-AGI-259.6 vs 9.9
  2. CritPt20.6 vs 5.7
  3. FrontierMath Tier 458.5 vs 21.9

Every shared benchmark34 · grouped by area

Reasoning 5

BenchmarkGPT-5MARGINGPT-5.6 Luna
ARC-AGI-29.9 ◆◆ 59.6
CritPt5.720.6
GPQA Diamond85.491.1
SimpleBench56.7 ◆◆ 46.8

Coding 5

BenchmarkGPT-5MARGINGPT-5.6 Luna
LMArena · WebDev1418 ◆◆ 1520
SciCode42.953.6
SWE-bench Pro41.8 ◆62.7

Agentic 3

BenchmarkGPT-5MARGINGPT-5.6 Luna
BrowseComp54.983.3
GDPVal20.347.2

Long Context 1

BenchmarkGPT-5MARGINGPT-5.6 Luna
AA-LCR78.283.7

Math 2

BenchmarkGPT-5MARGINGPT-5.6 Luna

Multimodal 3

BenchmarkGPT-5MARGINGPT-5.6 Luna
LMArena · Vision1208 ◆◆ 1259
CharXiv (RQ)81.182.7
MMMU-Pro74.278.6

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 withALL PAIRINGS →

Compare GPT-5.6 Luna withALL PAIRINGS →