Compare / Claude Opus 5.5 vs Inkling Small

Claude Opus 5.5 vs Inkling Small

Which is cheaper, which is more capable, and which does better at each kind of work, from 19 results on 3 sources that measured both models.

AnthropicClaude Opus 5.5 Released 22 Sep 2026 · $4.00 in · $20.00 out
Thinking MachinesInkling Small Released 15 Jul 2026 · $0.45 in · $1.20 out
Claude Opus 5.5 wins 18Inkling Small wins 1

Of the 19 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Claude Opus 5.5 or Inkling Small? The short answer

Pick Claude Opus 5.5 if quality matters most: it scores higher (Intelligence Index 57.6 against 25.7). Pick Inkling Small if cost matters more: it costs 13 times less per token. Inkling Small is also faster.

  • Inkling Small is cheaper: $0.64 against $8.00 per million tokens, 13 times less.
  • Claude Opus 5.5 scores higher on the Artificial Analysis Intelligence Index: 57.6 against 25.7.
  • Inkling Small writes faster: 181 tokens a second against 96.
  • Claude Opus 5.5 is newer: released 22 Sep 2026, against 15 Jul 2026 for Inkling Small.
  • On third-party benchmarks, on the results both models have: Claude Opus 5.5 does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

57.6
Intelligence Index
25.7
$8.00
Price per million tokens, blendedlower is better
$0.64
96
Output speed, tokens a second
181
1,000,000
Context window, tokens
524,288

Every fact side by side

Claude Opus 5.5Inkling Small
Price per million tokens$4.00 in · $20.00 out$0.45 in · $1.20 out
Blended (3 in : 1 out)$8.00$0.64
Cheapest host, blended$8.00 (Amazon Bedrock)–
Cached input, per million$0.20 cached input–
Intelligence Index57.625.7
Spring Prompt overall82–
Output speed, tokens a second96181
Context window1,000,000 tokens524,288 tokens
Released22 Sep 2026 (newer)15 Jul 2026
WeightsClosedOpen
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 13 of 32 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 7 of 32 not measured
User surveysPlanning a user survey and reading its results without being misled 4 of 23 not measured
Marketing planningPlanning a year of ad spend without overspending 9 of 32 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 3 of 159 80 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 3 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 1 of 187 68 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 5 of 169 101 of 169
Sticking to the factsSummarising without inventing things, and factual answers 3 of 139 119 of 139
Speed under pressureGood decisions against a real clock (fast chess) 36 of 36 7 of 35

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureClaude Opus 5.5Inkling Small
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 4 · 131 of 387 measured 1,504high reasoning 1,405
Overall · Text factualityArena rating, higher is better 2 · 104 of 163 measured 1,507high reasoning 1,426
Business, management and finance · TextArena rating, higher is better 10 · 125 of 380 measured 1,489high reasoning 1,409
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 1 · 76 of 249 measured 57.6max reasoning 25.7
Humanity's Last Exam% of questions, higher is better 1 · 74 of 250 measured 61.4%max reasoning 33.3%
Terminal-Bench 4.0% of tasks, higher is better 3 · 59 of 120 measured 59.6%max reasoning 1.0%
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 4 · 66 of 76 measured 72.2%max reasoning 19.1%xhigh reasoning
Show all 19 results (12 more)
MeasureClaude Opus 5.5Inkling Small
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results
Confirmed task success · AgentIPS effect estimate, higher is better 4 · 46 of 48 measured 0.14high reasoning, arena agent -0.20arena agent
Creative writing · TextArena rating, higher is better 2 · 192 of 385 measured 1,516high reasoning 1,311
Expert prompts · TextArena rating, higher is better 6 · 106 of 338 measured 1,541high reasoning 1,445
Instruction following · TextArena rating, higher is better 2 · 134 of 387 measured 1,517high reasoning 1,394
Praise over complaint · AgentIPS effect estimate, higher is better 3 · 46 of 48 measured 0.31high reasoning, arena agent -0.22arena agent
Steerability · AgentIPS effect estimate, higher is better 4 · 48 of 48 measured 0.10high reasoning, arena agent -0.14arena agent
Tool grounding · AgentIPS effect estimate, higher is better 6 · 40 of 48 measured 0.00high reasoning, arena agent -0.00arena agent
Writing, literature and language · TextArena rating, higher is better 2 · 175 of 386 measured 1,519high reasoning 1,342
Artificial Analysis reported by Artificial Analysis · 4 results
Long-context reasoning (AA-LCR)% of questions, higher is better 5 · 83 of 241 measured 84.7%max reasoning 75.7%
Output speedtokens per second, higher is better 46 · 18 of 78 measured 96.0max reasoning 181
SciCode% of problems, higher is better 1 · 56 of 121 measured 66.9%max reasoning 49.7%
Time to first answer tokenseconds, lower is better 43 · 50 of 78 measured 6.89low reasoning 12.9

Quick answers

Is Claude Opus 5.5 better than Inkling Small?

Pick Claude Opus 5.5 if quality matters most: it scores higher (Intelligence Index 57.6 against 25.7). Pick Inkling Small if cost matters more: it costs 13 times less per token. Inkling Small is also faster.

Which is cheaper, Claude Opus 5.5 or Inkling Small?

Inkling Small is cheaper: $0.64 against $8.00 per million tokens, 13 times less.

Which is faster, Claude Opus 5.5 or Inkling Small?

Inkling Small writes about 181 tokens a second on its usual API, against 96 for Claude Opus 5.5 (Artificial Analysis).

Which is better for agents and tool use, Claude Opus 5.5 or Inkling Small?

Claude Opus 5.5 ranks 3 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 80 for Inkling Small.

Which is better for reasoning and knowledge, Claude Opus 5.5 or Inkling Small?

Claude Opus 5.5 ranks 1 of 187 models on sale for hard questions across science, maths and general knowledge, against 68 for Inkling Small.

Which is better for writing, Claude Opus 5.5 or Inkling Small?

Claude Opus 5.5 ranks 5 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 101 for Inkling Small.

Which is better for sticking to the facts, Claude Opus 5.5 or Inkling Small?

Claude Opus 5.5 ranks 3 of 139 models on sale for summarising without inventing things, and factual answers, against 119 for Inkling Small.

Which has the bigger context window, Claude Opus 5.5 or Inkling Small?

Claude Opus 5.5: 1,000,000 tokens, against 524,288 for Inkling Small.

Run Claude Opus 5.5 and Inkling Small on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.