BenchLeader
Menu

GPT-5.6 Sol vs Inkling 2 Small

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

Updated · Data from 12 sources

As of 13 Nov 2026, GPT-5.6 Sol is ahead of Inkling 2 Small on quality (65.3 vs 57.9 on the BenchLeader Index), but Inkling 2 Small is 17× cheaper at $0.475 vs $8.00 per 1M tokens blended. GPT-5.6 Sol leads in every category we measure both in. Inkling 2 Small streams ~1.5× faster.

Key facts (as of 13 Nov 2026)

  • GPT-5.6 Sol scores 65.3 on the BenchLeader Index and Inkling 2 Small scores 57.9 (BenchLeader, 13 Nov 2026).
  • GPT-5.6 Sol costs $8.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 13 Nov 2026).
  • Inkling 2 Small streams ~1.5× faster than GPT-5.6 Sol (Artificial Analysis, 7-day median, 13 Nov 2026).
  • Of the 26 benchmarks both models have, GPT-5.6 Sol leads 21 (BenchLeader, 13 Nov 2026).
GPT-5.6 Sol benchmarks max OpenAI Inkling 2 Small benchmarks Thinking MachinesAdd a third model

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
CodingGPT-5.6 Sol66 vs 60 category score; SciCode 57.1% vs 52.3%Medium
Agents & tool useGPT-5.6 Sol68 vs 61 category score; τ³-Banking (AA) 44.3% vs 40.4%Medium
ReasoningGPT-5.6 Sol65 vs 53 category score; CritPt v2 hard subset (AA) 60.0% vs 35.0%High
KnowledgeGPT-5.6 Sol64 vs 54 category score; BioMysteryBench 71.1% vs 70.0%High
Long documentsEither67 vs 66 category score; AA-LCR v1.1 84.0% vs 83.3%Either
Images and other mediaGPT-5.6 Sol66 vs 64 category score; MMMU-Pro 83.4% vs 81.6%Medium
Chat quality (human preference)–Only Inkling 2 Small has an Arena rating (59 category score)Not comparable
Lowest costInkling 2 Small$0.475 vs $8.00 per 1M blended; agentic coding session $0.022 vs $0.320–
Fastest first answerEither68.5 s (GPT-5.6 Sol (max)) vs 63.9 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 Sol (max) leads on quality: 65.3 vs 57.9.
  • GPT-5.6 Sol (max) is stronger in agents & tools, coding, knowledge, long context, multimodal, reasoning.
  • Inkling 2 Small is 17× cheaper ($0.475 vs $8.00 per 1M blended).

At a glance

SpecGPT-5.6 SolInkling 2 Small
DeveloperOpenAIThinking Machines
Released9 Jul 20265 Nov 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-5.6 Sol (max)Inkling 2 Small
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.400$0.300 / $1.00 / –

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 Sol (max)Inkling 2 SmallLeader
Reasoning64.752.8GPT-5.6 Sol
Coding65.860.3GPT-5.6 Sol
Agents & tools67.661.1GPT-5.6 Sol
Maths70.0–not comparable
Knowledge63.853.5GPT-5.6 Sol
Instruction following71.2–not comparable
Human preference–58.6not comparable
Multimodal65.964.0GPT-5.6 Sol
Long context66.766.4level

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 & toolsKnowledgeLong contextMultimodalGPT-5.6 Sol, Reasoning: 64.7GPT-5.6 Sol, Coding: 65.8GPT-5.6 Sol, Agents & tools: 67.6GPT-5.6 Sol, Knowledge: 63.8GPT-5.6 Sol, Long context: 66.7GPT-5.6 Sol, Multimodal: 65.9Inkling 2 Small, Reasoning: 52.8Inkling 2 Small, Coding: 60.3Inkling 2 Small, Agents & tools: 61.1Inkling 2 Small, Knowledge: 53.5Inkling 2 Small, Long context: 66.4Inkling 2 Small, Multimodal: 64.0

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

Model, click to add or removeIndex

Where sources disagree

Across the 26 benchmarks both have, GPT-5.6 Sol leads 21, Inkling 2 Small leads 5. Every overall index that rates both puts GPT-5.6 Sol ahead.

Overall indexGPT-5.6 Sol (max)Inkling 2 SmallLeader
BenchLeader Index65.357.9GPT-5.6 Sol
Arena Text1485†1412GPT-5.6 Sol

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 Sol (max)Inkling 2 Small
Blended price per 1M tokens$8.00$0.475
Input / output per 1M$4.00 / $20.00$0.300 / $1.00
Cached input per 1M$0.400–
Price per task: chat reply$0.0076$0.0004
Price per task: summarize a 30-page report$0.060$0.0042
Price per task: code edit$0.054$0.0033
Price per task: agentic coding session$0.320$0.022
Price per task: structured extraction$0.012$0.0008
Agentic coding session, input mostly cached$0.158–
Cost per benchmark task (AA Index)–$1.18
Output tokens per task (AA Index)–150k
Of which reasoning–88k
Time per task (AA Index)–28 min
Output speed94 tok/s90 tok/s
Time to first answer68.5 s63.9 s
Time to a complete answer157.3 s163.6 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.6 Sol (max) scores 65.3 and takes 68 s to its first answer token; GPT-5.6 Sol (xhigh) scores 63.9 in 27 s, GPT-5.6 Sol (high) scores 63.4 in 16 s. Inkling 2 Small scores 57.9 and takes 64 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

152 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 Sol (max)Inkling 2 Small
BenchLeader IndexBenchLeader65.357.9
Agents & tools scoreBenchLeader67.661.1
Coding scoreBenchLeader65.860.3
Instruction following scoreBenchLeader71.2–
Knowledge scoreBenchLeader63.853.5
Long context scoreBenchLeader66.766.4
Maths scoreBenchLeader70.0–
Multimodal scoreBenchLeader65.964.0
Reasoning scoreBenchLeader64.752.8
Human preference scoreBenchLeader–58.6
Blended price $/MBenchLeader$8.00$0.475
Output speedBenchLeader94 tok/s90 tok/s
Time to first answerBenchLeader68.5 s63.9 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.5%–
SimpleBenchSimpleBench64.8%†–
Arena Hard PromptsArena (LMArena)1511†1438
LiveBench 1.0 ReasoningLiveBench91.7%–
GPQA Diamond (AA)Artificial Analysis94.1%–
Humanity's Last Exam (AA)Artificial Analysis49.5%44.1%
HLE-Diamond (AA)Artificial Analysis–28.7%
GPQA Diamond (Vals)Vals AI95.2%–
EnigmaEvalScale AI SEAL37.1%†–
Kagi LLM BenchmarkKagi LLM Benchmark67.0%†–
ARC-AGI-1ARC Prize96.5%96.5%†
ARC-AGI-2ARC Prize92.5%81.7%†
ARC-AGI-3ARC Prize7.8%–
CritPtArtificial Analysis32.3%–
CritPt v2 hard subset (AA)Artificial Analysis60.0%35.0%
MysteryMechanismVals AI33.3%25.2%
Chess PuzzlesEpoch AI Benchmarking Hub59.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub58.0%–
LMCAEpoch AI Benchmarking Hub58.4%–
DTBenchEpoch AI Benchmarking Hub95.5%–
ForecastBenchForecastBench65.7%–
BTF-3Epoch AI Benchmarking Hub13.7%–
Coding
SciCodeSciCode57.1%52.3%
WeirdMLWeirdML87.0%–
FrontierCodeCognition47.5%†–
Show all 152 benchmarks
MetricPublisherGPT-5.6 Sol (max)Inkling 2 Small
Coding
GSO-BenchGSO-Bench76.5%†–
Arena CodingArena (LMArena)1533†1485
Arena WebDevArena (LMArena)1615†1647
LiveBench 1.0 CodingLiveBench83.9%–
LiveCodeBenchVals AI82.6%–
IOIVals AI91.2%–
SWE-bench (Vals)Vals AI96.2%–
Code MigrationVals AI52.9%–
ProgramBenchVals AI1.5%0.5%
SWE-bench MultimodalVals AI–43.1%
Vibe Code Bench 1-100Vals AI20.0%–
Vibe Code Bench v1.1Vals AI80.5%81.5%
SWE Atlas: Codebase QnAScale AI SEAL46.0%†–
SWE Atlas: Test WritingScale AI SEAL45.9%†–
MirrorCodeEpoch AI Benchmarking Hub20.0%†–
Surface Evolver BenchEpoch AI Benchmarking Hub93.1%†–
DeepSWE v1.1Epoch AI Benchmarking Hub72.7%–
CursorBenchCursor41.7%–
ALE-BenchEpoch AI Benchmarking Hub2176.9–
FrontierSWEEpoch AI Benchmarking Hub32.2%–
Terminal-Bench 4.0 (AA)Artificial Analysis39.9%13.1%
Terminal-Bench 2.1 (AA)Artificial Analysis88.0%81.3%
Startrise FrontendStartrise66.2%†–
GameBench 2 OverallDuelLab GameBench 266.7†–
GameBench 2 by reasoning settingDuelLab GameBench 279.7†–
Design Arena WebsiteDesign Arena1319†1335
FrontierCode 2.0 (AA)Artificial Analysis–25.4%
Agents & tools
Terminal-BenchTerminal-Bench38.5%13.0%†
OSWorld-Verified 2.0OSWorld27.3%–
APEX-AgentsMercor51.4%†46.8%
Arena AgentArena (LMArena)4.6†2.5
LiveBench Agentic CodingLiveBench56.2%–
Terminal-Bench HardArtificial Analysis65.9%–
τ²-Bench Telecom (AA)Artificial Analysis85.1%–
Terminal-Bench 2.1 (Vals)Vals AI85.8%–
MCP AtlasScale AI SEAL–85.4%
HiL-BenchScale AI SEAL32.3%†–
τ³-bench Bankingτ²-bench46.9%†–
GDPval-AA v2.1Artificial Analysis–1630
τ³-Banking (AA)Artificial Analysis44.3%40.4%
ITBench SRE (AA)Artificial Analysis56.2%–
Analyst Agent (AA)Artificial Analysis47.5%51.3%
CUA-benchVals AI8.3%–
CyberBenchVals AI76.3%72.7%
Finance Agent v2Vals AI53.8%–
Finance Agent v2.1Vals AI–67.5%
Harvey's Legal Agent Benchmark v1.1Vals AI–21.7%
Harvey's Legal Agent Benchmark v1Vals AI2.5%–
Legal Research BenchVals AI48.1%46.6%
SkillsBenchVals AI54.1%–
SREBenchVals AI30.5%1.9%
Tax Agent BenchVals AI31.1%38.9%
Terminal-Bench 4.0 (Vals)Vals AI37.9%12.6%
Terminal-Bench ScienceVals AI20.0%2.9%
Time Horizon Index: KSPVals AI23.8%–
Web Search IndexVals AI43.6%–
Arena SearchArena (LMArena)1255†–
BALROGBALROG60.0%–
PostTrainBenchEpoch AI Benchmarking Hub31.0%–
GBAEvalEpoch AI Benchmarking Hub52.6%†–
Vending-Bench 2Andon Labs9619.4†–
AutomationBenchArtificial Analysis60.1%45.6%
GDP.pdf (AA)Artificial Analysis27.2%25.2%
EnterpriseOps-GymArtificial Analysis42.9%46.8%
AA-Briefcase v1.1Artificial Analysis14791527
Design Arena AgenticDesign Arena1231†1374
Terminal-Bench-Science 0.1 (AA)Artificial Analysis22.4%5.7%
FACTS SearchGoogle92.9%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub89.1%–
FrontierMath Tier 4Epoch AI Benchmarking Hub82.9%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
ProofBenchVals AI83.0%–
LiveBench MathematicsLiveBench96.2%–
Arena MathsArena (LMArena)1494†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub69.7%–
LiveBench 1.0 Data AnalysisLiveBench79.8%–
AA-Omniscience v1.1Artificial Analysis–16.1
MMLU-ProVals AI89.1%–
LegalBenchVals AI87.0%–
CorpFinVals AI64.4%–
TaxEvalVals AI74.8%–
PRBench FinanceScale AI SEAL50.5%–
PRBench LegalScale AI SEAL50.5%–
BioMysteryBenchVals AI71.1%70.0%
Excel Modeling BenchmarkVals AI72.3%–
Excel Modeling Benchmark v1.1Vals AI–69.5%
MedCodeVals AI44.0%–
MedScribeVals AI85.2%–
Public Benefits Bench v1.1Vals AI66.5%–
DrugDiscoveryBenchScale AI SEAL56.5%–
EBR-benchEpoch AI Benchmarking Hub44.8%–
GDP.pdfEpoch AI Benchmarking Hub30.7%–
AA-Omniscience v1.1: accuracyArtificial Analysis–33.8%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–73.3%
Instruction following
LiveBench LanguageLiveBench87.7%–
LiveBench Instruction FollowingLiveBench71.8%–
IFBenchArtificial Analysis72.7%–
Arena Instruction FollowingArena (LMArena)1490†1410
Human preference
Arena TextArena (LMArena)1485†1412
EQ-Bench 4EQ-Bench1236†–
Arena Creative WritingArena (LMArena)1471†1345
Arena Multi-turnArena (LMArena)1491†1415
Arena Longer QueriesArena (LMArena)1498†1410
Multimodal
Arena VisionArena (LMArena)1282†–
MMMU-ProArtificial Analysis83.4%81.6%
MMMU-Pro (Vals)Vals AI88.8%–
MortgageTaxVals AI67.3%–
SAGEVals AI–88.6%
GeoBenchGeoBench73.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub33.6%†–
Code2Video-AAArtificial Analysis–1020
AA-3DArtificial Analysis–1027
Long context
AA-LCR v1.1Artificial Analysis84.0%83.3%
Arena DocumentArena (LMArena)1487†–
MLCRArtificial Analysis30.0%20.6%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub163.0†–
LiveBench 1.0LiveBench81.0%–
AA Intelligence Index v5.0Artificial Analysis–30.6
AA Intelligence Index v4.3.2Artificial Analysis47.0–
AA Progress Index v1Artificial Analysis331.5–
Vals IndexVals AI–56.1
Vals Finance IndexVals AI–61.5%
Vals RSI IndexVals AI23.9%–
Vals Science IndexVals AI41.5%32.7%
Vals Multimodal IndexVals AI72.6%–
Safety & honesty
FORTRESSScale AI SEAL20.1%†16.2%
Metadata
AA Openness IndexArtificial Analysis–38.9

Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), 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: BenchLeader Index 58.4 → 57.9.
  • Inkling 2 Small: 2 new results (FORTRESS, Design Arena Agentic).
  • GPT-5.6 Sol (max): 1 score revision.
  • Inkling 2 Small: 2 new results (MysteryMechanism, Vals Science Index); 1 score revision.
  • GPT-5.6 Sol (max): BenchLeader Index 65.8 → 65.3.
  • Inkling 2 Small: 3 new results (SciCode, APEX-Agents, MLCR).
  • GPT-5.6 Sol (max): 1 score revision.
  • 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.
  • Inkling 2 Small: 1 new result (Arena WebDev).

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

GPT-5.6 Sol vs Inkling 2 Small: questions

Is GPT-5.6 Sol better than Inkling 2 Small?
GPT-5.6 Sol (max) leads on quality: 65.3 vs 57.9. The BenchLeader Index combines every independent quality benchmark; GPT-5.6 Sol (max) is ahead overall as of 13 Nov 2026, but check the category scores for your use.
GPT-5.6 Sol vs Inkling 2 Small: which is cheaper, and will that change?
Inkling 2 Small is cheaper today: $0.475 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.6 Sol or Inkling 2 Small better for coding?
GPT-5.6 Sol scores higher in coding (66 vs 60 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 57.1% for GPT-5.6 Sol against 52.3% for Inkling 2 Small.
Which is faster, GPT-5.6 Sol or Inkling 2 Small?
Inkling 2 Small streams ~1.5× faster (94 vs 90 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.6 Sol or Inkling 2 Small better for agents and tool use?
GPT-5.6 Sol scores higher in agentic tasks (68 vs 61 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 44.3% for GPT-5.6 Sol against 40.4% for Inkling 2 Small.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (67 vs 66). Both take about 1.1M tokens: GPT-5.6 Sol 1,050,000, Inkling 2 Small 1,048,576.
Which has lower latency?
Inkling 2 Small answers first: 63.9 s against 68.5 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 Sol vs Inkling 2 Small?
Across the 26 benchmarks both have, GPT-5.6 Sol leads 21, Inkling 2 Small leads 5. Every overall index that rates both puts GPT-5.6 Sol ahead.
When was Inkling 2 Small released?
Inkling 2 Small was released on 5 Nov 2026.