ComplexConstraints (Surge) (ComplexConstraints)
We show this table for reference; we do not rank on it.
An instruction-following benchmark from Surge AI that tests whether a model satisfies many simultaneous, interacting constraints in one response.
Benchmark score on ComplexConstraints — November 13, 2026
We compile the ComplexConstraints rows from provider self-reports. Inkling 2 Small leads the table at 44.5%. We do not use these results to rank models overall.
1 modelInstruction FollowingCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (1 model)
The one result on this page was reported by the lab that built the model.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Inkling 2 SmallThinking Machines LabReported by Thinking Machines Lab | 44.5% | Reported by Thinking Machines Lab | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
How to read this leaderboard
Operator receipt: 1 sourced row is currently displayable on this page; the leading published row is Inkling 2 Small at 44.5%.
Honest limit: The task set is private, and the launch table says v1.0 while its source list says v1.1.
About ComplexConstraints
Year
2026
Tasks
Prompts with multiple interacting constraints
Format
Pass rate (%)
Difficulty
Constrained instruction following
Thinking Machines lists ComplexConstraints among the evaluations it takes from Surge and reports v1.0 scores in the Inkling 2 Small launch (November 5, 2026): DeepSeek-V4.1-Flash-1017 50.4%, Gemini 3.8 Flash 48.4%, Inkling 2 Small 44.5%, Muse Spark Open 41.3% and Kimi K3 37.9%.
Freshness and provenance
Version
ComplexConstraints 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does ComplexConstraints measure?
An instruction-following benchmark from Surge AI that tests whether a model satisfies many simultaneous, interacting constraints in one response.
Which model scores highest on ComplexConstraints?
Inkling 2 Small by Thinking Machines Lab currently leads with a score of 44.5% on ComplexConstraints.
How many models are evaluated on ComplexConstraints?
1 AI models have published results on ComplexConstraints in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.