Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Inkling

Claude Opus 4.8 leads Inkling on coding, 65.0 to 31.5 on the Vibe Coding Index, and Inkling costs 6.2x less per output token ($4.05 vs $25.00 per million). Updated October 21, 2026; 94 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace Inkling
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
92
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
2
vs boards won of 94 shared

Claude Opus 4.8 or Inkling: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 31.5 for Inkling.

Pick Inkling for output tokens 6.2x cheaper ($4.05 vs $25.00 per million) and a lower cost per solved task ($0.76 against $2.17).

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved task
Shared results
94
Claude Opus 4.8 only
36
Inkling only
8
Like-for-like categories
8 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
Claude Opus 4.8 65.0 from 6 benchmarks, Inkling 31.5 from 6 benchmarks.
Widest category
Math, 30.6 points apart on average over 6 shared benchmarks.
Widest single gap
LiveBench browser: Claude Opus 4.8 96.0% against Inkling 16.0%, 80.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Inkling $4.05 per million output tokens, 6.2x apart.
Context window
Claude Opus 4.8 takes 1M 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
CategoryClaude Opus 4.8BarsInklingTies
Coding180
Intelligence20
Agentic work100
Reasoning130
Math60
Knowledge101
Web design90
General241
All shared boards922
CodingLike-for-likeSix of these boards feed the Vibe Coding Index180
Coding benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
LiveBench coding77.3%64.0%Claude Opus 4.8
LMArena WebDev15561414Claude Opus 4.8
AA Coding Index74.352.1Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%85.5%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%77.6%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%0.5%Claude Opus 4.8
Vibe Code Bench (Vals AI)82.7%19.2%Claude Opus 4.8
Code migration (Vals AI)47.3%11.8%Claude Opus 4.8
ProgramBench (Vals AI)1.0%0.0%Claude Opus 4.8
IOI (Vals AI)Not measured14.9%Only Inkling measured
Terminal-Bench 2.1 (Vals AI)71.9%47.6%Claude Opus 4.8
Vibe Code Bench 1-100 (Vals AI)Not measured7.3%Only Inkling measured
SkillsBench (Vals AI)59.2%26.1%Claude Opus 4.8
CyberBench (Vals AI)Not measured66.8%Only Inkling measured
SciCode54.4%47.0%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%Not measuredOnly Claude Opus 4.8 measured
FrontierCode46.5%14.0%Claude Opus 4.8
FrontierSWENot measured4.1%Only Inkling measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%32.3%Claude Opus 4.8
ALE-BenchNot measured946.0Only Inkling measured
LMArena Text: coding14901466Claude Opus 4.8
LMArena Text: software and IT14881465Claude Opus 4.8
LMArena WebDev: React15571404Claude Opus 4.8
LMArena WebDev: HTML15431399Claude Opus 4.8
SciCode12.3%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
AA Intelligence Index41.825.0Claude Opus 4.8
Epoch Capabilities Index159.0148.4Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index100
Agentic work benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
AA Agentic Index41.922.5Claude Opus 4.8
Design Arena: agents building web apps12331196Claude Opus 4.8
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building mobile apps1222Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Android apps1232Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games1238Not measuredOnly Claude Opus 4.8 measured
Design Arena: HTML slides1221Not measuredOnly Claude Opus 4.8 measured
Design Arena: PowerPoint slides1227Not measuredOnly Claude Opus 4.8 measured
Design Arena: spreadsheets1270Not measuredOnly Claude Opus 4.8 measured
LiveBench research81.8%59.9%Claude Opus 4.8
LiveBench browser96.0%16.0%Claude Opus 4.8
LiveBench long agentic48.3%14.1%Claude Opus 4.8
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)53.9%46.6%Claude Opus 4.8
Tax Agent Bench (Vals AI)30.0%15.3%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%28.4%Claude Opus 4.8
Harvey's Legal Agent Benchmark (Vals AI)Not measured3.8%Only Inkling measured
Excel Modeling Benchmark (Vals AI)69.4%38.4%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Claude Opus 4.8 measured
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%Not measuredOnly Claude Opus 4.8 measured
APEX-Agents48.9%33.8%Claude Opus 4.8
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787Not measuredOnly Claude Opus 4.8 measured
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
GPQA Diamond92.4%87.1%Claude Opus 4.8
LiveBench reasoning89.2%78.3%Claude Opus 4.8
MMMU Pro (Vals AI)86.6%78.5%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)92.0%87.2%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)48.7%31.9%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%88.3%Claude Opus 4.8
ARC-AGI92.5%79.5%Claude Opus 4.8
ARC-AGI-272.1%36.5%Claude Opus 4.8
SimpleBench64.8%50.0%Claude Opus 4.8
Chess puzzles52.0%21.0%Claude Opus 4.8
Mystery game puzzles36.0%Not measuredOnly Claude Opus 4.8 measured
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821451Claude Opus 4.8
LMArena Text: expert15031466Claude Opus 4.8
LMArena Text: hard prompts in English14871448Claude Opus 4.8
LMArena Vision: diagrams1315Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: homework1337Not measuredOnly Claude Opus 4.8 measured
Kagi LLM Benchmark88.8%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
OTIS Mock AIME98.3%88.9%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%33.3%Claude Opus 4.8
FrontierMath, tier 456.1%4.9%Claude Opus 4.8
ProofBench69.0%0.0%Claude Opus 4.8
LMArena Text: math14861479Claude Opus 4.8
LMArena Text: mathematical work14971460Claude Opus 4.8
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
MMLU Pro89.6%86.3%Claude Opus 4.8
LegalBench (Vals AI)83.6%83.0%Claude Opus 4.8
CorpFin (Vals AI)66.7%68.6%Inkling
TaxEval (Vals AI)75.6%75.3%Claude Opus 4.8
MortgageTax (Vals AI)69.9%64.0%Claude Opus 4.8
MedCode (Vals AI)53.2%41.2%Claude Opus 4.8
SimpleQA Verified53.0%40.3%Claude Opus 4.8
LMArena Text: science14771455Claude Opus 4.8
LMArena Text: medicine and healthcare14641447Claude Opus 4.8
LMArena Text: legal and government14771448Claude Opus 4.8
LMArena Text: business and finance14581438Claude Opus 4.8
FACTS Benchmark Suite53.5%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
Design Arena: websites12591224Claude Opus 4.8
Design Arena: UI components12571201Claude Opus 4.8
Design Arena: game dev12641166Claude Opus 4.8
Design Arena: data viz12401159Claude Opus 4.8
Design Arena: 3D12231161Claude Opus 4.8
Design Arena: all code categories12551206Claude Opus 4.8
Design Arena: SVG11941110Claude Opus 4.8
Design Arena: ASCII art12771089Claude Opus 4.8
LiveBench design78.8%58.3%Claude Opus 4.8
GeneralLike-for-likePublic boards, shown as published, kept out of the index241
General benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
Vals IndexNot measured29.0%Only Inkling measured
LiveBench data analysis66.0%72.8%Inkling
Public Benefits Bench (Vals AI)68.1%58.5%Claude Opus 4.8
SAGE (Vals AI)54.8%36.5%Claude Opus 4.8
MedScribe (Vals AI)85.8%85.4%Claude Opus 4.8
Vals Multimodal Index70.9%49.4%Claude Opus 4.8
IFBench62.2%Not measuredOnly Claude Opus 4.8 measured
Long context reasoning (AA-LCR)77.7%77.3%Claude Opus 4.8
DTBench94.9%87.5%Claude Opus 4.8
LMCA57.5%37.6%Claude Opus 4.8
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
LMArena Text14611442Claude Opus 4.8
LMArena Text: instruction following14761425Claude Opus 4.8
LMArena Text: creative writing14541390Claude Opus 4.8
LMArena Vision1294Not measuredOnly Claude Opus 4.8 measured
LMArena Text: English14681442Claude Opus 4.8
LMArena Text: non-English14501434Claude Opus 4.8
LMArena Text: Chinese15061493Claude Opus 4.8
LMArena Text: German14721445Claude Opus 4.8
LMArena Text: Japanese14421429Claude Opus 4.8
LMArena Text: Korean14311403Claude Opus 4.8
LMArena Text: French14811455Claude Opus 4.8
LMArena Text: Spanish14651449Claude Opus 4.8
LMArena Text: Russian14741430Claude Opus 4.8
LMArena Text: Polish14591450Claude Opus 4.8
LMArena Text: multi-turn14761437Claude Opus 4.8
LMArena Text: longer queries14831435Claude Opus 4.8
LMArena Text: writing and language14611404Claude Opus 4.8
LMArena Text: entertainment and media14401394Claude Opus 4.8
LMArena Vision: English1293Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: Chinese1346Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: reading text1303Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: humor1282Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: creative writing1301Not measuredOnly Claude Opus 4.8 measured
LMArena Document1475Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.8 and Inkling
BenchmarkClaude Opus 4.8InklingLeader
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

Claude Opus 4.8$0.018Fits in one request
Inkling$0.0030Fits in one request

Inkling costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Inkling$0.061Fits in one request

Inkling costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
Inkling$0.235Fits in one request

Inkling 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 Claude Opus 4.8 and Inkling
SpecificationAnthropic Claude Opus 4.8Thinking Machines Inkling
MakerAnthropicThinking Machines
WeightsNo public weights listedOpen weights
ReleasedMay 27, 2026July 17, 2026
Context window1M524K
Input $/Mtok$5.00$0.975
Output $/Mtok$25.00$4.05
Coding index65.031.5
Independent measurements behind it66
Cost per solved task$2.17$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Inkling for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 31.5 for Inkling. Pick Inkling for output tokens 6.2x cheaper ($4.05 vs $25.00 per million) and a lower cost per solved task ($0.76 against $2.17).

Which is cheaper, Claude Opus 4.8 or Inkling?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Inkling costs $0.975 and $4.05. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Inkling $0.76.

Which has the bigger context window, Claude Opus 4.8 or Inkling?

Claude Opus 4.8, with 1M tokens against 524K.

How many benchmarks is the Claude Opus 4.8 vs Inkling comparison based on?

94 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 6 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

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-opus-4-8-vs-thinkingmachines-inkling" title="Claude Opus 4.8 vs Inkling, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-opus-4-8-vs-thinkingmachines-inkling">LLMBenchmark.ai, Claude Opus 4.8 vs Inkling</a></p>