Thinking Machines Lab model product
Inkling 2 Small
Inkling 2 Small is a multimodal Mixture-of-Experts model from Thinking Machines Lab with 594B total parameters and 17B active parameters.
Updated Nov 11, 2026. Default version: Inkling 2 Small
LLMBoard Score74.0Inkling 2 Small
Coverage0%11 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Inkling 2 Small Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Inkling 2 Small Benchmark Results
Benchmark scores for Inkling 2 Small.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA-Briefcase | Score1,527.00 points | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score85.00% | Rank03 | Participants42 | Percentile95.12% | EvidenceC | Evaluated |
| BenchmarkTau3 Banking | Score40.40% | Rank03 | Participants22 | Percentile90.48% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA | Score1,630.00 points | Rank07 | Participants19 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score82.20% | Rank07 | Participants124 | Percentile95.12% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score90.20% | Rank08 | Participants76 | Percentile90.67% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score81.60% | Rank10 | Participants76 | Percentile88.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,649.47 rating | Rank10 | Participants109 | Percentile91.67% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score93.00% | Rank12 | Participants265 | Percentile95.83% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score2.08% | Rank13 | Participants43 | Percentile71.43% | EvidenceA | Evaluated |
| BenchmarkArtificial Analysis | Score30.60% | Rank14 | Participants14 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score2.11% | Rank15 | Participants43 | Percentile66.67% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score2.57% | Rank16 | Participants43 | Percentile64.29% | EvidenceA | Evaluated |
| BenchmarkCharXiv-R | Score85.60% | Rank20 | Participants64 | Percentile69.84% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score0.08% | Rank20 | Participants43 | Percentile54.76% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score-3.57% | Rank23 | Participants43 | Percentile47.62% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score-1.53% | Rank33 | Participants43 | Percentile23.81% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score44.10% | Rank34 | Participants118 | Percentile71.79% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,422.85 rating | Rank95 | Participants134 | Percentile29.32% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,412.11 rating | Rank110 | Participants221 | Percentile50.45% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,403.18 rating | Rank113 | Participants221 | Percentile49.09% | EvidenceA | Evaluated |
Inkling 2 Small Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categorywebdev-html | Rank06 | Rating / score1,661.09 | Votes128 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank10 | Rating / score1,649.47 | Votes964 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank10 | Rating / score1,649.47 | Votes964 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank11 | Rating / score1,661.87 | Votes623 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank13 | Rating / score0.02 | VotesN/A | Observations16.7K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank15 | Rating / score0.02 | VotesN/A | Observations1.7K | Result date |
| Arenaagent bash reliability | Categoryoverall | Rank16 | Rating / score0.03 | VotesN/A | Observations57.6K | Result date |
| Arenaagent | Categoryoverall | Rank20 | Rating / score0.00 | VotesN/A | Observations529K | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank23 | Rating / score-0.04 | VotesN/A | Observations844 | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank33 | Rating / score-0.02 | VotesN/A | Observations452.2K | Result date |
| Arenatext | Categoryexpert | Rank38 | Rating / score1,479.05 | Votes251 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank48 | Rating / score1,488.26 | Votes251 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank62 | Rating / score1,442.87 | Votes399 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank69 | Rating / score1,456.64 | Votes616 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank76 | Rating / score1,487.46 | Votes616 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank78 | Rating / score1,429.25 | Votes923 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank79 | Rating / score1,485.60 | Votes616 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank86 | Rating / score1,407.20 | Votes923 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank86 | Rating / score1,469.83 | Votes958 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank88 | Rating / score1,441.46 | Votes909 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank88 | Rating / score1,463.70 | Votes583 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank89 | Rating / score1,443.24 | Votes958 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank90 | Rating / score1,451.28 | Votes1,658 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank90 | Rating / score1,429.96 | Votes405 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank91 | Rating / score1,413.73 | Votes405 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank91 | Rating / score1,390.88 | Votes705 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank91 | Rating / score1,464.04 | Votes958 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank92 | Rating / score1,403.69 | Votes819 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank94 | Rating / score1,384.12 | Votes639 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank95 | Rating / score1,411.60 | Votes1,759 | ObservationsN/A | Result date |
Inkling 2 Small Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Inkling 2 Small Runtime Performance
Provider-specific output speed and catalog latency for Inkling 2 Small. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Inkling 2 Small Specifications
Technical details for the model's default version.
- Version
- Inkling 2 Small
- Released
- Nov 5, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 594B
- Context window
- 256K
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Inkling 2 Small Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionInkling 2 Small | Released | LLMBoard74.05 | Parameters594B | Context256K | Max outputN/A | Open weightsNo | LicenseProprietary |
Models similar to Inkling 2 Small
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
TM
Inkling
Thinking Machines Lab
TM
Inkling Small
Thinking Machines Lab
GO
Google
Gemini 3.5 Flash
ME
Muse Spark Open
Meta
GOGoogle
Gemini 3.6 Flash
BY
Seed 2.1 Pro
ByteDance
What is Inkling 2 Small?
Key information about Inkling 2 Small and its available data.
It accepts text and image inputs and generates text, with variable thinking effort. Its model card lists a context window of up to 1M tokens.
Data as of 2026-11-10.
FAQ
Common questions about Inkling 2 Small.
When was Inkling 2 Small released?
Inkling 2 Small's default version was released on Nov 5, 2026.
How much does Inkling 2 Small cost?
No official standard PAYG price is currently available for Inkling 2 Small.
Who created Inkling 2 Small?
Inkling 2 Small was created by Thinking Machines Lab.
What is the context window for Inkling 2 Small?
The default version has a 256K token context window.
Is Inkling 2 Small open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Inkling 2 Small?
No provider offering is currently linked to the default version.