BenchLeader

Inkling 2 Small vs Qwen3.7 Plus

Full profiles: Inkling 2 Small (Thinking Machines) and Qwen3.7 Plus (Alibaba): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6 on the BenchLeader Index, inside the ±7.8 margin), and Inkling 2 Small is 1.5× cheaper at $0.475 vs $0.700 per 1M tokens blended. Choose Inkling 2 Small for coding (60 vs 44), agents & tools (61 vs 46), and long context (66 vs 61), where it also streams ~1.5× faster; choose Qwen3.7 Plus for human preference (64 vs 59) and reasoning (54 vs 53).

Key facts (as of 16 Nov 2026)

  • Inkling 2 Small scores 57.9 on the BenchLeader Index and Qwen3.7 Plus scores 57.6 (BenchLeader, 16 Nov 2026).
  • Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.7 Plus costs $0.700 per 1M tokens blended (list price, 16 Nov 2026).
  • Inkling 2 Small streams ~1.5× faster than Qwen3.7 Plus (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 28 benchmarks both models have, Inkling 2 Small leads 21 (BenchLeader, 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 44 category score; SciCode 52.3% vs 46.1%High
Agents & tool useInkling 2 Small61 vs 46 category score; τ³-Banking (AA) 40.4% vs 17.5%High
ReasoningQwen3.7 Plus54 vs 53 category score; Arena Hard Prompts 1473 vs 1438Medium
Long documentsInkling 2 Small66 vs 61 category score; AA-LCR v1.1 83.3% vs 73.0%Medium
Images and other mediaInkling 2 Small64 vs 62 category score; MMMU-Pro 81.6% vs 80.5%Medium
Chat quality (human preference)Qwen3.7 Plus64 vs 59 on Arena votesMedium
Lowest costInkling 2 Small$0.475 vs $0.700 per 1M blended; agentic coding session $0.022 vs $0.030–
Fastest first answerEither49.0 s (Inkling 2 Small) vs 49.8 s (Qwen3.7 Plus) 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

  • Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6, within the ±7.8 margin).
  • Inkling 2 Small is stronger in agents & tools, coding, long context, multimodal.
  • Qwen3.7 Plus is stronger in human preference, reasoning.
  • Inkling 2 Small is 1.5× cheaper ($0.475 vs $0.700 per 1M blended).
  • Inkling 2 Small streams 1.7× faster (100 vs 57 tokens per second).

At a glance

SpecInkling 2 SmallQwen3.7 Plus
DeveloperThinking MachinesAlibaba
Released5 Nov 20262 Jun 2026
Context window (tokens)1,048,5761,000,000
Compared atInkling 2 SmallQwen3.7 Plus
Open weightsNoNo
Price in / out / cached input per 1M$0.300 / $1.00 / $0.030$0.400 / $1.60 / $0.080

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.

CategoryInkling 2 SmallQwen3.7 PlusLeader
Reasoning52.854.4Qwen3.7 Plus
Coding60.343.9Inkling 2 Small
Agents & tools61.145.5Inkling 2 Small
Maths–64.2not comparable
Knowledge53.5–not comparable
Instruction following–75.9not comparable
Human preference58.664.0Qwen3.7 Plus
Multimodal64.062.3Inkling 2 Small
Long context66.461.0Inkling 2 Small

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 contextMultimodalHumanpreferenceInkling 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: 58.6Qwen3.7 Plus, Reasoning: 54.4Qwen3.7 Plus, Coding: 43.9Qwen3.7 Plus, Agents & tools: 45.5Qwen3.7 Plus, Long context: 61.0Qwen3.7 Plus, Multimodal: 62.3Qwen3.7 Plus, Human preference: 64.0

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 28 benchmarks both have, Inkling 2 Small leads 21, Qwen3.7 Plus leads 7. Every overall index that rates both puts Qwen3.7 Plus ahead.

Overall indexInkling 2 SmallQwen3.7 PlusLeader
BenchLeader Index57.957.6neck and neck
Arena Text14121455Qwen3.7 Plus

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.

MeasureInkling 2 SmallQwen3.7 Plus
Blended price per 1M tokens$0.475$0.700
Input / output per 1M$0.300 / $1.00$0.400 / $1.60
Cached input per 1M$0.030$0.080
Price per task: chat reply$0.0004$0.0006
Price per task: summarize a 30-page report$0.0042$0.0058
Price per task: code edit$0.0033$0.0048
Price per task: agentic coding session$0.022$0.030
Price per task: structured extraction$0.0008$0.0011
Agentic coding session, input mostly cached$0.0099$0.016
Cost per benchmark task (AA Index)$1.18–
Output tokens per task (AA Index)150k–
Of which reasoning88k–
Time per task (AA Index)25 min–
Output speed100 tok/s57 tok/s
Time to first answer49.0 s49.8 s
Time to a complete answer, last measured 13 Nov 2026163.6 s114.8 s

Each model is compared at its best-ranked reasoning-effort setting. Inkling 2 Small scores 57.9 and takes 49 s to its first answer token. Qwen3.7 Plus scores 57.6 and takes 50 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

104 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.

MetricPublisherInkling 2 SmallQwen3.7 Plus
BenchLeader IndexBenchLeader57.957.6
Agents & tools scoreBenchLeader61.145.5
Coding scoreBenchLeader60.343.9
Human preference scoreBenchLeader58.664.0
Knowledge scoreBenchLeader53.5–
Long context scoreBenchLeader66.461.0
Multimodal scoreBenchLeader64.062.3
Reasoning scoreBenchLeader52.854.4
Instruction following scoreBenchLeader–75.9
Maths scoreBenchLeader–64.2
Blended price $/MBenchLeader$0.475$0.700
Output speedBenchLeader100 tok/s57 tok/s
Time to first answerBenchLeader49.0 s49.8 s
Context windowBenchLeader1,048,576 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–87.9%
Arena Hard PromptsArena (LMArena)14381473
GPQA Diamond (AA)Artificial Analysis–90.0%
Humanity's Last Exam (AA)Artificial Analysis44.1%35.6%
HLE-Diamond (AA)Artificial Analysis28.7%13.9%
ARC-AGI-1ARC Prize96.5%†–
ARC-AGI-2ARC Prize81.7%†–
CritPtArtificial Analysis–9.1%
CritPt v2 hard subset (AA)Artificial Analysis35.0%–
MysteryMechanismVals AI25.2%–
Arena ExpertArena (LMArena)14881485
Mystery Game PuzzlesEpoch AI Benchmarking Hub–17.0%
LMCAEpoch AI Benchmarking Hub–37.6%
DTBenchEpoch AI Benchmarking Hub–84.0%
Coding
SciCodeSciCode52.3%46.1%
FrontierCodeCognition–10.2%
Arena CodingArena (LMArena)14851500
Arena WebDevArena (LMArena)1647–
Code MigrationVals AI–12.9%
ProgramBenchVals AI0.5%–
SWE-bench MultimodalVals AI43.1%–
Vibe Code Bench v1.1Vals AI81.5%46.4%
SWE Atlas v1.1Scale AI SEAL61.9%–
SWE Atlas v1.1: Codebase QnAScale AI SEAL74.2%–
SWE Atlas v1.1: Test WritingScale AI SEAL58.1%–
Show all 104 benchmarks
MetricPublisherInkling 2 SmallQwen3.7 Plus
Coding
SWE Atlas v1.1: RefactoringScale AI SEAL53.3%–
SWE-Bench Pro V2Scale AI SEAL97.7%–
SWE-Bench Pro V2 HARDScale AI SEAL86.3%–
Terminal-Bench 4.0 (AA)Artificial Analysis13.1%1.0%
Terminal-Bench 2.1 (AA)Artificial Analysis81.3%61.0%
GameBench 2 by reasoning settingDuelLab GameBench 2–17.7†
Design Arena WebsiteDesign Arena13351261
FrontierCode 2.0 (AA)Artificial Analysis25.4%–
Agents & tools
Terminal-BenchTerminal-Bench13.0%†–
OSWorld-Verified 2.0OSWorld–2.8%
APEX-AgentsMercor46.8%–
Arena AgentArena (LMArena)2.5-8
Terminal-Bench HardArtificial Analysis–47.0%
τ²-Bench Telecom (AA)Artificial Analysis–93.0%
Terminal-Bench 2.1 (Vals)Vals AI–52.8%
MCP AtlasScale AI SEAL85.4%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–13.3%
GDPval-AA v2.1Artificial Analysis1630774
τ³-Banking (AA)Artificial Analysis40.4%17.5%
Analyst Agent (AA)Artificial Analysis51.3%–
APEX-Agents (AA)Artificial Analysis–22.4%
CyberBenchVals AI72.7%–
Finance Agent v2Vals AI–38.2%
Finance Agent v2.1Vals AI67.5%–
Harvey's Legal Agent Benchmark v1.1Vals AI21.7%–
Harvey's Legal Agent Benchmark v1Vals AI–0.0%
Legal Research BenchVals AI46.6%16.4%
SkillsBenchVals AI–54.3%
SREBenchVals AI1.9%–
Tax Agent BenchVals AI38.9%10.5%
Terminal-Bench 4.0 (Vals)Vals AI12.6%–
Terminal-Bench ScienceVals AI2.9%–
Arena Agent Task CompletionArena (LMArena)3.3-10.8
AutomationBenchArtificial Analysis45.6%17.4%
GDP.pdf (AA)Artificial Analysis25.2%12.2%
EnterpriseOps-GymArtificial Analysis46.8%40.6%
AA-Briefcase v1.1Artificial Analysis1527915
Design Arena AgenticDesign Arena1315–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis5.7%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–34.4%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–93.3%
ArXivMathMathArena31.9%–
BrokenArXivMathArena63.2%–
Arena MathsArena (LMArena)–1465
Knowledge
AA-Omniscience v1.1Artificial Analysis16.1–
BioMysteryBenchVals AI70.0%–
Excel Modeling BenchmarkVals AI–49.4%
Excel Modeling Benchmark v1.1Vals AI69.5%–
AA-Omniscience v1.1: accuracyArtificial Analysis33.8%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis73.3%–
Instruction following
IFBenchArtificial Analysis–78.0%
Arena Instruction FollowingArena (LMArena)14101447
Human preference
Arena TextArena (LMArena)14121455
Arena Creative WritingArena (LMArena)13451431
Arena Multi-turnArena (LMArena)14151464
Arena Longer QueriesArena (LMArena)14101465
Multimodal
Arena VisionArena (LMArena)–1277
MMMU-ProArtificial Analysis81.6%80.5%
MortgageTaxVals AI–66.2%
SAGEVals AI88.6%89.2%
Humanity's Sixth SenseScale AI SEAL33.3%–
VIALS-AAHandshake AI42.9%–
Code2Video-AAArtificial Analysis1020–
AA-3DArtificial Analysis1027–
Long context
AA-LCR v1.1Artificial Analysis83.3%73.0%
Arena DocumentArena (LMArena)–1446
MLCRArtificial Analysis20.6%8.9%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–147.9
AA Intelligence Index v5.0.1Artificial Analysis30.6–
AA Intelligence Index v4.3.2Artificial Analysis–25.2
AA Progress Index v1Artificial Analysis–283.9
Vals IndexVals AI56.1–
Vals Finance IndexVals AI61.5%–
Vals Science IndexVals AI32.7%–
Vals Multimodal IndexVals AI–53.9%
Vals Legal IndexVals AI73.9%–
Safety & honesty
FORTRESSScale AI SEAL16.2%–
DistressBenchScale AI SEAL82.3%–
Metadata
AA Openness IndexArtificial Analysis38.9–

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).
  • 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.
  • 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.
  • Inkling 2 Small: 1 new result (Arena WebDev).
  • Qwen3.7 Plus: 1 score revision.

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

Inkling 2 Small vs Qwen3.7 Plus: questions

Is Inkling 2 Small better than Qwen3.7 Plus?
Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6, within the ±7.8 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.
Inkling 2 Small vs Qwen3.7 Plus: which is cheaper, and will that change?
Inkling 2 Small is cheaper today: $0.475 against $0.700 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Inkling 2 Small or Qwen3.7 Plus better for coding?
Inkling 2 Small scores higher in coding (60 vs 44 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 52.3% for Inkling 2 Small against 46.1% for Qwen3.7 Plus.
Which is faster, Inkling 2 Small or Qwen3.7 Plus?
Inkling 2 Small streams ~1.5× faster (100 vs 57 output tokens per second, Artificial Analysis 7-day median).
Is Inkling 2 Small or Qwen3.7 Plus better for agents and tool use?
Inkling 2 Small scores higher in agentic tasks (61 vs 46 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 40.4% for Inkling 2 Small against 17.5% for Qwen3.7 Plus.
More questions (4)
Which is better for long documents?
Inkling 2 Small scores higher on long-context benchmarks (66 vs 61). Both take about 1M tokens: Inkling 2 Small 1,048,576, Qwen3.7 Plus 1,000,000.
Which has lower latency?
Inkling 2 Small answers first: 49.0 s against 49.8 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 Inkling 2 Small vs Qwen3.7 Plus?
Across the 28 benchmarks both have, Inkling 2 Small leads 21, Qwen3.7 Plus leads 7. Every overall index that rates both puts Qwen3.7 Plus ahead.
When was Inkling 2 Small released?
Inkling 2 Small was released on 5 Nov 2026.