Trillion Labs
Updated 5 h ago · first seen 11 Sept 2026
company_01M29A5BV5GHXYHF9PRFS41SJ7
Specification
No structured attributes yet.
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
0
Source tiers
—
Freshest observation
—
Conflicts
None
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
| Model | Params | Context | Openness | Released | Status | Quality |
|---|---|---|---|---|---|---|
| tri-21b-think-preview | — | 32K | open-weights | — | deprecated | 44 |
| tri-21b-think-v0-5 | — | 32K | open-weights | — | active | 44 |
No relations recorded.
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
No claims recorded yet
New model: tri-21b-think-v0-5 (Trillion Labs)
artificial_analysisNew model: tri-21b-think-preview (Trillion Labs)
artificial_analysistri-21b-think-v0-5 scores 0.76% on Terminal-Bench
artificial_analysistri-21b-think-v0-5 scores 80.99% on τ²-bench
artificial_analysistri-21b-think-v0-5 scores 54.63% on IFBench
artificial_analysistri-21b-think-v0-5 scores 5.93% on Humanity's Last Exam
artificial_analysistri-21b-think-v0-5 scores 60.1% on GPQA
artificial_analysistri-21b-think-v0-5 scores 8.99 on Artificial Analysis Intelligence Index
artificial_analysistri-21b-think-preview scores 2.27% on Terminal-Bench
artificial_analysistri-21b-think-preview scores 93.27% on τ²-bench
artificial_analysistri-21b-think-preview scores 47.14% on IFBench
artificial_analysistri-21b-think-preview scores 5.79% on Humanity's Last Exam
artificial_analysistri-21b-think-preview scores 53.84% on GPQA
artificial_analysistri-21b-think-preview scores 9.59 on Artificial Analysis Intelligence Index
artificial_analysis
No documents recorded