Skip to content
Bencher

Models · Thinking Machines Lab · Out sinceReleased 30 Jul 2026

Inkling Small

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary

Inkling Small is made by Thinking Machines Lab. We don't have enough test results yet to rank it. It's cheap to use.

Auto-created from OpenRouter catalog; verify details.

Writing & creativity
—
Research & analysis
—
Coding
—
Price
Cheap$0.45 / $1.20
Price per 1M (blended)Blended / 1M
$0.64
MemoryContext
524K
Longest answerMax output
—
Test resultsResults
5 (5 independent5 indep.)
Out sinceReleased
30 Jul 2026
Made byVendor
Thinking Machines Lab
UnderstandsInputs
—

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Read more

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as thinkingmachines/inkling-small.

Route it as thinkingmachines/inkling-small at $0.45 in / $1.20 out per 1M tokens, 524K context. Listed since 30 Jul 2026.

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
NotesNotes
MCP Atlas79.2%DefaultInkling-smallIndependent testIndependentScale AI SEAL ↗1 Oct 2026—rank 2 (Scale rank accounts for CI); ±2.5; entry added 2026-07-30
ProgramBench (fully resolved)0.5%Defaultreasoning_effort=0.99Independent testIndependentVals.ai ↗29 Sep 2026mini-SWE-agent±0.5 stderr; $0.479/test; strict fully-resolved rate
SWE-bench Verified82.2%Defaultreasoning_effort=0.99Independent testIndependentVals.ai ↗1 Sep 2026bash-only (single bash tool) agent±1.712 stderr; $0.134/test; Vals archived SWE-bench Verified on 2026-09-01 (saturated)
Vals CorpFin v269.6%Defaultvals id thinkingmachines/inkling-small; reasoning_effort=0.99Independent testIndependentVals.ai ↗12 Aug 2026—vals id thinkingmachines/inkling-small; rank 6/134; ±0.906 stderr; $0.025455/test
Vals TaxEval v275.5%Defaultvals id thinkingmachines/inkling-small; reasoning_effort=0.99Independent testIndependentVals.ai ↗1 Sep 2026—vals id thinkingmachines/inkling-small; rank 18/145; ±0.837 stderr; $0.017501/test