reasoning
Trinity-Large-Thinking
Arcee AI open reasoning model for long-horizon agents and multi-turn tool calling, post-trained from Trinity-Large-Base.
Levelmodel
Classreasoning
Parameters398B
Context512,000
Released1 Apr 2026
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reported
AIME 2025 2025math
vendor-reported
96.3
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
GPQA Diamondknowledge and reasoning
vendor-reported
76.3
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
IFBenchknowledge and reasoning
vendor-reported
52.3
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
MMLU-Proknowledge and reasoning
vendor-reported
83.4
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
SWE-bench Verifiedcoding
Marked with an asterisk on the model cardvendor-reported
63.2
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
tau2-benchagents and tool use
Telecom domainvendor-reported
94.7
050100
Score in %. Higher is better.
Trinity-Large-Thinking model card
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
finetune
Trinity-Large-Base is the parent (finetune)high confidenceHugging Face base_modelWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Runtimes
Identity
- Developer
- Arcee AI
- Family
- Trinity-Large
- Released
- 1 Apr 2026 sourcesannouncement page
- Weights published
- 1 Apr 2026
- Record checked
- 11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- MoE Sparse MoE with 4 active experts; explicit reasoning traces in think blocks
- Total parameters
- 398B sources
- Active parameters
- 13B
- Checkpoint parameters
- –
- Note
- About 398B total and about 13B active per token
- Context length
- 512,000 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- OpenMDW License v1.1 sources
- Access routes
- API, open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Blog says Apache 2.0, but the LICENSE file in the weights repository is OpenMDW-1.1; the licence file governs
- Runtimes
- vLLM
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Hugging Face language tags: en, es, fr, de, it, pt, ru, ar, hi, ko, zh
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperArcee AIstartup, USA
Arcee AIstartup, USAModelTrinity-Large-ThinkingArcee AI, reasoning
Trinity-Large-ThinkingArcee AI, reasoningUse CasesProcess Optimisation and Advanced Process ControlIndustrialChinese Medical LLMsHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025
Conch CementIn production, 23 Jun 2025
PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025Conch CementIn production, 23 Jun 2025PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.Organisations 1
Sources
- arcee.ai/blog/trinity-large-thinking https://www.arcee.ai/blog/trinity-large-thinking
- huggingface.co/arcee-ai/Trinity-Large-Thinking https://huggingface.co/arcee-ai/Trinity-Large-Thinking
- huggingface.co/arcee-ai/Trinity-Large-Thinking/raw/main/LICE... https://huggingface.co/arcee-ai/Trinity-Large-Thinking/raw/main/LICENSE
- openrouter.ai/arcee-ai/trinity-large-thinking https://openrouter.ai/arcee-ai/trinity-large-thinking
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Trinity-Large-Thinking", https://aurion.semai.id/models/arcee-ai-trinity-large-thinking/, records of October 2026.