Models / Inkling

Thinking Machines

Inkling

Inkling is strongest at reasoning and knowledge; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is DeepSeek-V4-Flash (0423), at $0.15 per million tokens against $1.76.

Results 16 Nov 2026 · 26 results · 5 sources

Test Inkling on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.00 in · $4.05 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
232 tokens a second; on its test prompt the answer starts after 10.9 s, thinking time included
Artificial Analysis, on its usual API, at xhigh reasoning
Intelligence Index
25.0
Artificial Analysis, at xhigh reasoning
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Thinking Machines, based in the US
Weights published
Released
15 Jul 2026
524,288 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 74th of 185Claude Opus 5.5 – $1.76 blended, 65th percentilecheapest: Mistral Nemo 12th of 65Nemotron 3.5 Super VL
Models priced $1–3 per million tokens 20th of 34Muse Spark 1.3 – sets this group 2nd of 9Muse Spark 1.3
Models with similar intelligence sets this group – $1.76 blended, 76th percentilecheapest: DeepSeek-V4-Flash (0423) 3rd of 9Nemotron 3.5 Super VL
Models writing 200 or more tokens a second 7th of 14Muse Spark 1.3 – $1.76 blended, 92nd percentilecheapest: gpt-oss-20b sets this group
Models from developers based in the US 44th of 92Claude Opus 5.5 – $1.76 blended, 47th percentilecheapest: Gemma 3 4B 10th of 33Nemotron 3.5 Super VL
Open-weights models 28th of 104MiMo-V2.6-Pro – $1.76 blended, 89th percentilecheapest: Mistral Nemo 7th of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 72nd of 159 available · 17th of 31 at its price
BenchmarkInklingRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 1.0% 56th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 55.1% 53rd of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 29.1% 35th of 104 Grok 4.6 50.7%
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 45th of 51 available · 9th of 12 at its price
BenchmarkInklingRank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 33.8% 34th of 37 Claude Sonnet 5.5 75.5%
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 76th of 187 available · 20th of 35 at its price
BenchmarkInklingRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 25.0 74th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 31.9% 71st of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 87.2% 59th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 66th of 169 available · 17th of 28 at its price
BenchmarkInklingRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,441 63rd of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 71st of 139 available · 14th of 26 at its price
BenchmarkInklingRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,451 48th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 40.3% 41st of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Inkling at $1.76 blended, Intelligence Index 25.0. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $1.76 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Togethernot stated$1.00$4.05$1.76

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

InklingMuse Spark 1.3
most intelligent at $1–3 per million tokens
DeepSeek-V4-Flash (0423)
cheapest with similar intelligence
Nemotron 3.5 Super VL
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $1.76 $2.00$0.15$0.24$8.00
Tokens a second 232 254–41196
Intelligence Index 25.0 48.124.426.557.6
Spring Prompt overall – 59––82
Rank among available models, by use case
Product listings – 17th––13th
Decks from an analysis – 25th––7th
User surveys – –––4th
Marketing planning – 25th––9th
Agents and tool use 72nd of 159 13th59th132nd3rd
Professional work 45th of 51 8th––3rd
Reasoning and knowledge 76th of 187 11th69th74th1st
Writing 66th of 169 7th63rd–5th
Sticking to the facts 71st of 139 11th81st–3rd
Speed under pressure – 33rd–––

Shaded figures are better than Inkling's. A dash means no result.

Where it has been measured

2nd fastest of the 9 models priced $1–3 per million tokens, and 3rd fastest of the 9 models with similar intelligence. 20th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the bottom quarter for professional work.

Every result

26 published results from 5 sources, each in the source's own units, with the configuration that produced it.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 33.8% 36 of 39 Inkling 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better -0.21
-0.24–-0.18
50 of 50 Inkling (arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better -0.23
-0.25–-0.20
49 of 50 Inkling (arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better -0.12
-0.14–-0.10
49 of 50 Inkling (arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.00
29 of 50 Inkling (arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,451
1,448–1,455
66 of 182 Inkling 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,444
1,436–1,452
92 of 406 Inkling 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,379
1,371–1,387
143 of 411 Inkling 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,473
1,463–1,483
84 of 363 Inkling 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,426
1,420–1,432
102 of 413 Inkling 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,441
1,437–1,446
95 of 413 Inkling 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,398
1,391–1,406
128 of 412 Inkling 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 11 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 52.1 95 of 187 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 25.0 154 of 413 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 87.2% 102 of 360 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 31.9% 140 of 419 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 77.3% 128 of 407 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 232 15 of 137 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 47.0% 136 of 205 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 55.1% 98 of 188 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 1.0% 134 of 204 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 10.9 62 of 137 Inkling (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 29.1% 66 of 175 Inkling (xhigh reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 40.3% 46 of 85 Inkling (xhigh reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

tau2-bench · reported by tau2-bench · 2 results
MeasureValueRankConfigurationDated
tau2 v1.0.1, banking knowledge, alltools retrieval: consistency (pass^4)% of tasks, higher is better 11.3% 14 of 21 Inkling (max reasoning, tau2) 24 Jul 2026
tau2 v1.0.1, banking knowledge, alltools retrieval: task success (pass^1)% of tasks, higher is better 25.0% 16 of 21 Inkling (max reasoning, tau2) 24 Jul 2026

Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

Will Inkling work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.