Inkling 2 Small
Inkling 2 Small is capable in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
30results on30benchmarks
- 30 vendor-reported
From 1 source · latest Nov 6, 2026 · How verification works
Inkling 2 Small benchmark results
30 results on 30 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
23.5% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro81.60Nov 6, 2026MMMU Pro (Standard 10)
0 of 3 ranked benchmarks measured
- 70.60Nov 6, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- Covert Action with Goal (Apollo Research)0.00Nov 6, 2026
- Covert Action with No Goal (Apollo Research)8.00Nov 6, 2026
- HoneyBench v0.2-alpha: Reward Hacking (Goodhart Labs)44.00Nov 6, 2026
- Destructive actions (Internal)4.70Nov 6, 2026
- Covert misbehavior (Internal)11.80Nov 6, 2026
- Misbehavior (Internal)14.90Nov 6, 2026
Show 22 more resultsHide 22 results
- Apex-Accounting v1.1 pass@114.50Nov 6, 2026
- CritPt v2 Full55.70Nov 6, 2026
- CritPt v2 Hard35.00Nov 6, 2026
- DAYJOB (Finance)14.30Nov 6, 2026
- DeepSWE 1.172.10Nov 6, 2026DeepSWE v1.1
- Diligence Bench Best harness58.10Nov 6, 2026
- DistressBench82.00Nov 6, 2026
- EnterpriseBench-CoreCraft71.80Nov 6, 2026
- FORTRESS (ORS)20.40Nov 6, 2026
- GDPval-AA 2.11630.00Nov 6, 2026GDPVal-AA v2.1
- HLE-Diamond28.70Nov 6, 2026
- Humanity’s Sixth Sense33.30Nov 6, 2026
- 70.50Nov 6, 2026
- PatchEval79.60Nov 6, 2026
- PostTrain Bench v1.231.90Nov 6, 2026
- 97.80Nov 6, 2026
- SWEBench Pro v2 (Hard)86.30Nov 6, 2026
- Terminal-Bench-Science 0.15.70Nov 6, 2026Terminal Bench Science v0.1
- Vals CyberBench72.70Nov 6, 2026
- Vals Finance Index61.50Nov 6, 2026
- Vals Legal Index73.90Nov 6, 2026
- Vibe Code Bench v1.181.60Nov 6, 2026
Inkling 2 Small: common questions
Who makes Inkling 2 Small?
Inkling 2 Small is made by Thinking Machines.
When was Inkling 2 Small released?
Inkling 2 Small was released on Nov 5, 2026, according to Thinking Machines's own announcement.
What is Inkling 2 Small good at?
Inkling 2 Small is capable in multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
How many benchmarks has Inkling 2 Small been tested on?
We track 30 results for Inkling 2 Small on 30 benchmarks from 1 source. The latest was recorded on Nov 6, 2026.
About this record
Where Inkling 2 Small's numbers come from, and every name it appears under.
- Tracked since
- Nov 6, 2026
- Newest source mention
- Nov 6, 2026
Where the results come from
Verification: 30 scores · 0 independently verified · 30 vendor-reported. How these tiers are assigned
From 1 source on 1 site. thinkingmachines.ai supplies all of them. Bars are coloured by trust tier.
- thinkingmachines.ai30