Enter opens the highlighted result. Esc closes.

Qwen3 VL 235B A22B Instruct vs Inkling

Inkling leads Qwen3 VL 235B A22B Instruct on the Artificial Analysis Intelligence Index, 25.0 to 9.9, and Qwen3 VL 235B A22B Instruct costs 2.1x less per output token ($1.90 vs $4.05 per million). Updated October 22, 2026; 32 benchmarks have a result for both.

Replace Qwen3 VL 235B A22B Instruct Replace Inkling
Qwen3 VL 235B A22B InstructQwen
Coding
No data
Overall
No data
Output $/M
$1.90
0
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
32
vs boards won of 32 shared

Qwen3 VL 235B A22B Instruct or Inkling: which to pick

Only Inkling has a coding score, 31.5 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding.

Pick Qwen3 VL 235B A22B Instruct for output tokens 2.1x cheaper ($1.90 vs $4.05 per million).

Model AQwen3 VL 235B A22B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved task
Shared results
32
Qwen3 VL 235B A22B Instruct only
17
Inkling only
70
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Qwen3 VL 235B A22B Instruct not benchmarked, Inkling 31.5 from 6 benchmarks.
Widest category
Intelligence, 15.1 points apart on average over 1 shared benchmark.
Widest single gap
Humanity's Last Exam (Artificial Analysis run): Qwen3 VL 235B A22B Instruct 11.9% against Inkling 31.9%, 20.0 points apart on a 0 to 100 scale.
Output price
Qwen3 VL 235B A22B Instruct $1.90 against Inkling $4.05 per million output tokens, 2.1x apart.
Context window
Qwen3 VL 235B A22B Instruct takes 262K tokens, Inkling 524K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryQwen3 VL 235B A22B InstructBarsInklingTies
Coding02
Intelligence01
Reasoning05
Math02
Knowledge04
General018
All shared boards032
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
LiveBench codingNot measured64.0%Only Inkling measured
LMArena WebDevNot measured1414Only Inkling measured
AA Coding IndexNot measured52.1Only Inkling measured
LiveCodeBench (Vals AI)Not measured85.5%Only Inkling measured
SWE-bench Verified (Vals AI)Not measured77.6%Only Inkling measured
Terminal-Bench 4 (Vals AI)Not measured0.5%Only Inkling measured
Vibe Code Bench (Vals AI)Not measured19.2%Only Inkling measured
Code migration (Vals AI)Not measured11.8%Only Inkling measured
ProgramBench (Vals AI)Not measured0.0%Only Inkling measured
IOI (Vals AI)Not measured14.9%Only Inkling measured
Terminal-Bench 2.1 (Vals AI)Not measured47.6%Only Inkling measured
Vibe Code Bench 1-100 (Vals AI)Not measured7.3%Only Inkling measured
SkillsBench (Vals AI)Not measured26.1%Only Inkling measured
CyberBench (Vals AI)Not measured66.8%Only Inkling measured
LiveCodeBench (Artificial Analysis run)64.6%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
SciCodeNot measured47.0%Only Inkling measured
Terminal-Bench Hard (Artificial Analysis run)11.4%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
FrontierCodeNot measured14.0%Only Inkling measured
FrontierSWENot measured4.1%Only Inkling measured
WeirdMLNot measured32.3%Only Inkling measured
ALE-BenchNot measured946.0Only Inkling measured
LMArena Text: coding14381466Inkling
LMArena Text: software and IT14421465Inkling
LMArena WebDev: ReactNot measured1404Only Inkling measured
LMArena WebDev: HTMLNot measured1399Only Inkling measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
AA Intelligence Index9.925.0Inkling
Epoch Capabilities IndexNot measured148.4Only Inkling measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
Agentic work benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
AA Agentic IndexNot measured22.5Only Inkling measured
Design Arena: agents building web appsNot measured1196Only Inkling measured
LiveBench researchNot measured59.9%Only Inkling measured
LiveBench browserNot measured16.0%Only Inkling measured
LiveBench long agenticNot measured14.1%Only Inkling measured
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)Not measured46.6%Only Inkling measured
Tax Agent Bench (Vals AI)Not measured15.3%Only Inkling measured
Legal Research Bench (Vals AI)Not measured28.4%Only Inkling measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured3.8%Only Inkling measured
Excel Modeling Benchmark (Vals AI)Not measured38.4%Only Inkling measured
τ²-Bench Telecom54.1%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
APEX-AgentsNot measured33.8%Only Inkling measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
GPQA DiamondNot measured87.1%Only Inkling measured
LiveBench reasoningNot measured78.3%Only Inkling measured
MMMU Pro (Vals AI)Not measured78.5%Only Inkling measured
GPQA Diamond (Artificial Analysis run)77.2%87.2%Inkling
Humanity's Last Exam (Artificial Analysis run)11.9%31.9%Inkling
GPQA Diamond (Epoch AI run)Not measured88.3%Only Inkling measured
ARC-AGINot measured79.5%Only Inkling measured
ARC-AGI-2Not measured36.5%Only Inkling measured
SimpleBenchNot measured50.0%Only Inkling measured
Chess puzzlesNot measured21.0%Only Inkling measured
LMArena Text: hard prompts14281451Inkling
LMArena Text: expert14421466Inkling
LMArena Text: hard prompts in English14391448Inkling
LMArena Vision: diagrams1255Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: homework1277Not measuredOnly Qwen3 VL 235B A22B Instruct measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
AA Math Index88.3Not measuredOnly Qwen3 VL 235B A22B Instruct measured
AIME 2025 (Artificial Analysis run)88.3%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
OTIS Mock AIMENot measured88.9%Only Inkling measured
FrontierMath, tiers 1 to 3Not measured33.3%Only Inkling measured
FrontierMath, tier 4Not measured4.9%Only Inkling measured
ProofBenchNot measured0.0%Only Inkling measured
LMArena Text: math14251479Inkling
LMArena Text: mathematical work14191460Inkling
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
MMLU ProNot measured86.3%Only Inkling measured
LegalBench (Vals AI)Not measured83.0%Only Inkling measured
CorpFin (Vals AI)Not measured68.6%Only Inkling measured
TaxEval (Vals AI)Not measured75.3%Only Inkling measured
MortgageTax (Vals AI)Not measured64.0%Only Inkling measured
MedCode (Vals AI)Not measured41.2%Only Inkling measured
MMLU Pro (Artificial Analysis run)83.6%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
SimpleQA VerifiedNot measured40.3%Only Inkling measured
LMArena Text: science14441455Inkling
LMArena Text: medicine and healthcare14311447Inkling
LMArena Text: legal and government14381448Inkling
LMArena Text: business and finance14331438Inkling
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
Design Arena: websitesNot measured1224Only Inkling measured
Design Arena: UI componentsNot measured1198Only Inkling measured
Design Arena: game devNot measured1165Only Inkling measured
Design Arena: data vizNot measured1156Only Inkling measured
Design Arena: 3DNot measured1160Only Inkling measured
Design Arena: all code categoriesNot measured1205Only Inkling measured
Design Arena: SVGNot measured1108Only Inkling measured
Design Arena: ASCII artNot measured1089Only Inkling measured
LiveBench designNot measured58.3%Only Inkling measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
Vals IndexNot measured29.0%Only Inkling measured
LiveBench data analysisNot measured72.8%Only Inkling measured
Public Benefits Bench (Vals AI)Not measured58.5%Only Inkling measured
SAGE (Vals AI)Not measured36.5%Only Inkling measured
MedScribe (Vals AI)Not measured85.4%Only Inkling measured
Vals Multimodal IndexNot measured49.4%Only Inkling measured
IFBench56.5%Not measuredOnly Qwen3 VL 235B A22B Instruct measured
Long context reasoning (AA-LCR)63.7%77.3%Inkling
DTBenchNot measured87.5%Only Inkling measured
LMCANot measured37.6%Only Inkling measured
LMArena Text14201442Inkling
LMArena Text: instruction following14061425Inkling
LMArena Text: creative writing13661390Inkling
LMArena Vision1247Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Text: English14291442Inkling
LMArena Text: non-English14051434Inkling
LMArena Text: Chinese14631493Inkling
LMArena Text: German14241445Inkling
LMArena Text: Japanese13851429Inkling
LMArena Text: Korean13941403Inkling
LMArena Text: French14521455Inkling
LMArena Text: Spanish14281449Inkling
LMArena Text: Russian14081430Inkling
LMArena Text: Polish14191450Inkling
LMArena Text: multi-turn14281437Inkling
LMArena Text: longer queries14191435Inkling
LMArena Text: writing and language13921404Inkling
LMArena Text: entertainment and media13681394Inkling
LMArena Vision: English1256Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: Chinese1283Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: reading text1253Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: humor1209Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: captioning1281Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: recognizing things1249Not measuredOnly Qwen3 VL 235B A22B Instruct measured
LMArena Vision: creative writing1220Not measuredOnly Qwen3 VL 235B A22B Instruct measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3 VL 235B A22B Instruct and Inkling
BenchmarkQwen3 VL 235B A22B InstructInklingLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Qwen3 VL 235B A22B Instruct$0.0012Fits in one request
Inkling$0.0030Fits in one request

Qwen3 VL 235B A22B Instruct costs less

Repository review

50K input + 3K output tokens

Qwen3 VL 235B A22B Instruct$0.016Fits in one request
Inkling$0.061Fits in one request

Qwen3 VL 235B A22B Instruct costs less

Agent loop

200K input + 10K output tokens

Qwen3 VL 235B A22B Instruct$0.061Fits in one request
Inkling$0.235Fits in one request

Qwen3 VL 235B A22B Instruct costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Qwen3 VL 235B A22B Instruct and Inkling
SpecificationQwen3 VL 235B A22B InstructThinking Machines Inkling
MakerQwenThinking Machines
WeightsOpen weightsOpen weights
ReleasedSeptember 23, 2025July 17, 2026
Context window262K524K
Input $/Mtok$0.21$0.975
Output $/Mtok$1.90$4.05
Coding indexNot benchmarked31.5
Independent measurements behind it06
Cost per solved taskNot computable$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3 VL 235B A22B Instruct better than Inkling for coding?

Only Inkling has a coding score, 31.5 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding. Pick Qwen3 VL 235B A22B Instruct for output tokens 2.1x cheaper ($1.90 vs $4.05 per million).

Which is cheaper, Qwen3 VL 235B A22B Instruct or Inkling?

Qwen3 VL 235B A22B Instruct costs $0.21 per million input tokens and $1.90 per million output tokens; Inkling costs $0.975 and $4.05. Cost per solved task is known for Inkling only.

Which has the bigger context window, Qwen3 VL 235B A22B Instruct or Inkling?

Inkling, with 524K tokens against 262K.

How many benchmarks is the Qwen3 VL 235B A22B Instruct vs Inkling comparison based on?

32 benchmarks have a result for both models as of October 22, 2026. Qwen3 VL 235B A22B Instruct's coding index rests on 0 independent benchmarks and Inkling's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next