BenchLeader

GPT-5.6 Luna vs Inkling 2 Small

Full profiles: GPT-5.6 Luna (OpenAI) and Inkling 2 Small (Thinking Machines): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, GPT-5.6 Luna and Inkling 2 Small are neck and neck on quality (58.2 vs 57.9 on the BenchLeader Index, inside the ±5.2 margin), and they cost about the same at $0.450 vs $0.475 per 1M tokens blended. Choose GPT-5.6 Luna for human preference (64 vs 59) and fast first answers (28.1 s vs 49.0 s); choose Inkling 2 Small for multimodal (64 vs 60), agents & tools (61 vs 57), and coding (60 vs 56).

Key facts (as of 16 Nov 2026)

  • GPT-5.6 Luna scores 58.2 on the BenchLeader Index and Inkling 2 Small scores 57.9 (BenchLeader, 16 Nov 2026).
  • GPT-5.6 Luna costs $0.450 per 1M tokens blended (list price, 16 Nov 2026).
  • Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 20 benchmarks both models have, Inkling 2 Small leads 13 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, GPT-5.6 Luna is rated 1519 and Inkling 2 Small 1647 (LMArena, as published by 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingInkling 2 Small60 vs 56 category score; Arena WebDev 1647 vs 1519Medium
Agents & tool useInkling 2 Small61 vs 57 category score; τ³-Banking (AA) 40.4% vs 28.7%Medium
ReasoningInkling 2 Small53 vs 52 category score; Arena Hard Prompts 1438 vs 1475Medium
Long documentsEither66 vs 66 category score; AA-LCR v1.1 81.7% vs 83.3%Either
Images and other mediaInkling 2 Small64 vs 60 category score; MMMU-Pro 81.6% vs 78.5%Medium
Chat quality (human preference)GPT-5.6 Luna64 vs 59 on Arena votesMedium
Lowest costEither$0.450 vs $0.475 per 1M blended; agentic coding session $0.017 vs $0.022–
Fastest first answerGPT-5.6 Luna28.1 s (GPT-5.6 Luna (xhigh)) vs 49.0 s (Inkling 2 Small) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-5.6 Luna (xhigh) and Inkling 2 Small are neck and neck on quality (58.2 vs 57.9, within the ±5.2 margin).
  • GPT-5.6 Luna (xhigh) is stronger in human preference.
  • Inkling 2 Small is stronger in agents & tools, coding, long context, multimodal, reasoning.
  • They cost about the same ($0.450 per 1M blended).

At a glance

SpecGPT-5.6 LunaInkling 2 Small
DeveloperOpenAIThinking Machines
Released9 Jul 20265 Nov 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-5.6 Luna (xhigh)Inkling 2 Small
Open weightsNoNo
Price in / out / cached input per 1M$0.200 / $1.20 / $0.020$0.300 / $1.00 / $0.030

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-5.6 Luna (xhigh)Inkling 2 SmallLeader
Reasoning51.852.8Inkling 2 Small
Coding56.460.3Inkling 2 Small
Agents & tools57.161.1Inkling 2 Small
Maths65.7–not comparable
Knowledge–53.5not comparable
Human preference63.758.6GPT-5.6 Luna
Multimodal59.964.0Inkling 2 Small
Long context65.566.4level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsLong contextMultimodalHumanpreferenceGPT-5.6 Luna, Reasoning: 51.8GPT-5.6 Luna, Coding: 56.4GPT-5.6 Luna, Agents & tools: 57.1GPT-5.6 Luna, Long context: 65.5GPT-5.6 Luna, Multimodal: 59.9GPT-5.6 Luna, Human preference: 63.7Inkling 2 Small, Reasoning: 52.8Inkling 2 Small, Coding: 60.3Inkling 2 Small, Agents & tools: 61.1Inkling 2 Small, Long context: 66.4Inkling 2 Small, Multimodal: 64.0Inkling 2 Small, Human preference: 58.6

Not drawn, measured for fewer than two of these models: Maths, Knowledge, Instruction following.

Model, click to add or removeIndex

Where sources disagree

Across the 20 benchmarks both have, GPT-5.6 Luna leads 7, Inkling 2 Small leads 13. Independent sources split: GPT-5.6 Luna leads on Arena Text; Inkling 2 Small leads on AA Intelligence Index v5.0.1.

Overall indexGPT-5.6 Luna (xhigh)Inkling 2 SmallLeader
BenchLeader Index58.257.9neck and neck
AA Intelligence Index v5.0.123.8†30.6Inkling 2 Small
Arena Text14531412GPT-5.6 Luna

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGPT-5.6 Luna (xhigh)Inkling 2 Small
Blended price per 1M tokens$0.450$0.475
Input / output per 1M$0.200 / $1.20$0.300 / $1.00
Cached input per 1M$0.020$0.030
Price per task: chat reply$0.0004$0.0004
Price per task: summarize a 30-page report$0.0031$0.0042
Price per task: code edit$0.0030$0.0033
Price per task: agentic coding session$0.017$0.022
Price per task: structured extraction$0.0006$0.0008
Agentic coding session, input mostly cached$0.0087$0.0099
Cost per benchmark task (AA Index)–$1.18
Output tokens per task (AA Index)–150k
Of which reasoning–88k
Time per task (AA Index)–25 min
Output speed110 tok/s100 tok/s
Time to first answer28.1 s49.0 s
Time to a complete answer, last measured 13 Nov 2026101.7 s163.6 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.6 Luna (xhigh) scores 58.2 and takes 28 s to its first answer token; GPT-5.6 Luna (max) scores 56.2 in 59 s, GPT-5.6 Luna (high) scores 54.7 in 11 s. Inkling 2 Small scores 57.9 and takes 49 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

149 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-5.6 Luna (xhigh)Inkling 2 Small
BenchLeader IndexBenchLeader58.257.9
Agents & tools scoreBenchLeader57.161.1
Coding scoreBenchLeader56.460.3
Human preference scoreBenchLeader63.758.6
Long context scoreBenchLeader65.566.4
Maths scoreBenchLeader65.7–
Multimodal scoreBenchLeader59.964.0
Reasoning scoreBenchLeader51.852.8
Knowledge scoreBenchLeader–53.5
Blended price $/MBenchLeader$0.450$0.475
Output speedBenchLeader110 tok/s100 tok/s
Time to first answerBenchLeader28.1 s49.0 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.6%†–
SimpleBenchSimpleBench46.8%–
Arena Hard PromptsArena (LMArena)14751438
LiveBench 1.0 ReasoningLiveBench85.6%†–
GPQA Diamond (AA)Artificial Analysis89.5%–
Humanity's Last Exam (AA)Artificial Analysis37.0%44.1%
HLE-Diamond (AA)Artificial Analysis20.9%†28.7%
GPQA Diamond (Vals)Vals AI91.7%†–
Kagi LLM BenchmarkKagi LLM Benchmark49.1%†–
ARC-AGI-1ARC Prize87.7%96.5%†
ARC-AGI-2ARC Prize47.6%81.7%†
ARC-AGI-3ARC Prize0.0%–
CritPtArtificial Analysis20.6%–
CritPt v2 hard subset (AA)Artificial Analysis30.5%†35.0%
MysteryMechanismVals AI14.4%†25.2%
Arena ExpertArena (LMArena)14901488
Chess PuzzlesEpoch AI Benchmarking Hub43.0%†–
Mystery Game PuzzlesEpoch AI Benchmarking Hub21.0%†–
LMCAEpoch AI Benchmarking Hub48.5%–
DTBenchEpoch AI Benchmarking Hub89.1%–
Coding
SciCodeSciCode50.5%52.3%
WeirdMLWeirdML60.9%†–
FrontierCodeCognition39.8%†–
Arena CodingArena (LMArena)15031485
Arena WebDevArena (LMArena)15191647
Show all 149 benchmarks
MetricPublisherGPT-5.6 Luna (xhigh)Inkling 2 Small
Coding
LiveBench 1.0 CodingLiveBench82.9%†–
IOIVals AI61.8%†–
SWE-bench (Vals)Vals AI93.0%†–
Code MigrationVals AI44.5%†–
ProgramBenchVals AI0.0%†0.5%
SWE-bench MultimodalVals AI–43.1%
Vibe Code Bench 1-100Vals AI22.6%†–
Vibe Code Bench v1.1Vals AI77.1%†81.5%
SWE Atlas v1.1Scale AI SEAL–61.9%
SWE Atlas v1.1: Codebase QnAScale AI SEAL–74.2%
SWE Atlas v1.1: Test WritingScale AI SEAL–58.1%
SWE Atlas v1.1: RefactoringScale AI SEAL–53.3%
SWE-Bench Pro V2Scale AI SEAL–97.7%
SWE-Bench Pro V2 HARDScale AI SEAL–86.3%
MirrorCodeEpoch AI Benchmarking Hub21.1%†–
Surface Evolver BenchEpoch AI Benchmarking Hub61.9%†–
DeepSWE v1.1Epoch AI Benchmarking Hub56.9%–
CursorBenchCursor33.0%–
ALE-BenchEpoch AI Benchmarking Hub1667.4†–
WeirdML v3WeirdML5.2%–
Terminal-Bench 4.0 (AA)Artificial Analysis3.5%13.1%
Terminal-Bench 2.1 (AA)Artificial Analysis77.9%81.3%
Startrise FrontendStartrise65.0%†–
GameBench 2 OverallDuelLab GameBench 240.2†–
GameBench 2 by reasoning settingDuelLab GameBench 254–
Design Arena WebsiteDesign Arena1248†1335
FrontierCode 2.0 (AA)Artificial Analysis17.6%†25.4%
Agents & tools
Terminal-BenchTerminal-Bench17.6%†13.0%†
APEX-AgentsMercor43.0%†46.8%
Arena AgentArena (LMArena)–2.5
LiveBench Agentic CodingLiveBench48.4%†–
Terminal-Bench 2.1 (Vals)Vals AI79.0%†–
MCP AtlasScale AI SEAL–85.4%
GDPval-AA v2.1Artificial Analysis14071630
τ³-Banking (AA)Artificial Analysis28.7%40.4%
ITBench SRE (AA)Artificial Analysis40.3%†–
Analyst Agent (AA)Artificial Analysis–51.3%
APEX-Agents (AA)Artificial Analysis35.8%†–
CyberBenchVals AI73.6%†72.7%
Finance Agent v2Vals AI55.0%†–
Finance Agent v2.1Vals AI–67.5%
Harvey's Legal Agent Benchmark v1.1Vals AI–21.7%
Harvey's Legal Agent Benchmark v1Vals AI1.3%†–
Legal Research BenchVals AI36.5%†46.6%
SkillsBenchVals AI60.5%†–
SREBenchVals AI1.5%†1.9%
Tax Agent BenchVals AI24.8%†38.9%
Terminal-Bench 4.0 (Vals)Vals AI11.6%†12.6%
Terminal-Bench ScienceVals AI0.0%†2.9%
Arena Agent Task CompletionArena (LMArena)–3.3
BALROGBALROG45.6%†–
Vending-Bench 2Andon Labs4094.7†–
AutomationBenchArtificial Analysis42.6%45.6%
GDP.pdf (AA)Artificial Analysis23.8%25.2%
EnterpriseOps-GymArtificial Analysis40.8%†46.8%
AA-Briefcase v1.1Artificial Analysis12671527
Design Arena AgenticDesign Arena1149†1315
Terminal-Bench-Science 0.1 (AA)Artificial Analysis3.3%†5.7%
FACTS SearchGoogle87.0%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub82.1%†–
FrontierMath Tier 4Epoch AI Benchmarking Hub61.0%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub98.3%†–
ProofBenchVals AI60.0%†–
LiveBench MathematicsLiveBench87.2%†–
ArXivMathMathArena–31.9%
BrokenArXivMathArena–63.2%
Arena MathsArena (LMArena)1476–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub41.0%†–
LiveBench 1.0 Data AnalysisLiveBench78.0%†–
AA-Omniscience v1.1Artificial Analysis-17.1†16.1
MMLU-ProVals AI86.0%†–
LegalBenchVals AI84.0%†–
CorpFinVals AI64.2%†–
TaxEvalVals AI76.2%†–
BioMysteryBenchVals AI61.5%†70.0%
Excel Modeling BenchmarkVals AI67.1%†–
Excel Modeling Benchmark v1.1Vals AI–69.5%
MedCodeVals AI42.4%†–
MedScribeVals AI84.4%†–
Public Benefits Bench v1.1Vals AI61.2%†–
Access to Justice BenchmarkVals AI65.6%†–
Financial Coaching BenchVals AI69.3%†–
GDP.pdfEpoch AI Benchmarking Hub22.7%†–
AA-Omniscience v1.1: accuracyArtificial Analysis39.1%†33.8%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis7.7%†73.3%
FACTS ParametricGoogle50.6%†–
Instruction following
LiveBench LanguageLiveBench72.6%†–
LiveBench Instruction FollowingLiveBench60.1%†–
Arena Instruction FollowingArena (LMArena)14431410
Human preference
Arena TextArena (LMArena)14531412
EQ-Bench 4EQ-Bench1146†–
EQ-Bench Creative Writing v3EQ-Bench1832†–
Arena Creative WritingArena (LMArena)14111345
Arena Multi-turnArena (LMArena)14581415
Arena Longer QueriesArena (LMArena)14521410
Multimodal
Arena VisionArena (LMArena)1256–
MMMU-ProArtificial Analysis78.5%81.6%
MMMU-Pro (Vals)Vals AI85.0%†–
MortgageTaxVals AI67.3%†–
SAGEVals AI–88.6%
Humanity's Sixth SenseScale AI SEAL21.6%†33.3%
Blueprint-Bench 2Epoch AI Benchmarking Hub22.6%†–
Furniture AssemblyEpoch AI Benchmarking Hub42.5%†–
VIALS-AAHandshake AI–42.9%
Code2Video-AAArtificial Analysis–1020
AA-3DArtificial Analysis–1027
FACTS MultimodalGoogle37.4%†–
Long context
AA-LCR v1.1Artificial Analysis81.7%83.3%
Arena DocumentArena (LMArena)1460–
MLCRArtificial Analysis15.0%20.6%
FACTS GroundingGoogle52.5%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.7†–
LiveBench 1.0LiveBench73.6%†–
AA Intelligence Index v5.0.1Artificial Analysis23.8†30.6
AA Intelligence Index v4.3.2Artificial Analysis34.6–
AA Progress Index v1Artificial Analysis305.8–
Vals IndexVals AI–56.1
Vals Finance IndexVals AI–61.5%
Vals Science IndexVals AI25.3%†32.7%
Vals Multimodal IndexVals AI69.1%†–
Vals Legal IndexVals AI–73.9%
Safety & honesty
FORTRESSScale AI SEAL–16.2%
DistressBenchScale AI SEAL72.7%†82.3%
Metadata
AA Openness IndexArtificial Analysis–38.9

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Inkling 2 Small: 1 score revision; Inkling 2 Small cached input price moved from $0.060/M to $0.030/M (50% down).
  • GPT-5.6 Luna (xhigh): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Inkling 2 Small: 1 score revision.
  • Inkling 2 Small: BenchLeader Index 58.4 → 57.9.
  • Inkling 2 Small: 2 new results (FORTRESS, Design Arena Agentic).
  • Inkling 2 Small: 2 new results (MysteryMechanism, Vals Science Index); 1 score revision.
  • GPT-5.6 Luna (xhigh): 1 score revision.
  • Inkling 2 Small: 3 new results (SciCode, APEX-Agents, MLCR).
  • Inkling 2 Small: 8 new results (Arena Text, Arena Hard Prompts, Arena Coding…); 2 score revisions.
  • Inkling 2 Small: BenchLeader Index 57.5 → 58.4.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GPT-5.6 Luna vs Inkling 2 Small: questions

Is GPT-5.6 Luna better than Inkling 2 Small?
GPT-5.6 Luna (xhigh) and Inkling 2 Small are neck and neck on quality (58.2 vs 57.9, within the ±5.2 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
GPT-5.6 Luna vs Inkling 2 Small: which is cheaper, and will that change?
GPT-5.6 Luna is cheaper today: $0.450 against $0.475 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.6 Luna or Inkling 2 Small better for coding?
Inkling 2 Small scores higher in coding (60 vs 56 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1519 for GPT-5.6 Luna against 1647 for Inkling 2 Small.
Which is faster, GPT-5.6 Luna or Inkling 2 Small?
GPT-5.6 Luna streams faster (110 vs 100 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.6 Luna or Inkling 2 Small better for agents and tool use?
Inkling 2 Small scores higher in agentic tasks (61 vs 57 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 28.7% for GPT-5.6 Luna against 40.4% for Inkling 2 Small.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (66 vs 66). Both take about 1.1M tokens: GPT-5.6 Luna 1,050,000, Inkling 2 Small 1,048,576.
Which has lower latency?
GPT-5.6 Luna answers first: 28.1 s against 49.0 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on GPT-5.6 Luna vs Inkling 2 Small?
Across the 20 benchmarks both have, GPT-5.6 Luna leads 7, Inkling 2 Small leads 13. Independent sources split: GPT-5.6 Luna leads on Arena Text; Inkling 2 Small leads on AA Intelligence Index v5.0.1.
When was Inkling 2 Small released?
Inkling 2 Small was released on 5 Nov 2026.