Model profile
Trinity Large
Evidence summary
Trinity Large has an estimated overall rank of #240; its 90% source-sensitivity interval is #163–#250. Its behavior-only rank is #247; company governance moves the combined estimate to #240. Published evidence spans 4 evals and 4 of 7 behavior components. Its strongest relative result is SM-Bench (eq_boundaries, #29 of 73); its weakest is SM-Bench (ambiguous_interpretation, #71 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗trinity-large-thinking
- Hugging Face ↗arcee-ai/Trinity-Large-Preview
- OpenRouter ↗arcee-ai/trinity-large-preview
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #213 / 311 | 0.8665 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #73 / 105 | 0.15 | ↑ higher | Source ↗official | |
| DystopiaBenchbasaglia_score | #46 / 50 | 71.4 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #28 / 50 | 58.53 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #46 / 50 | 80.8 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #47 / 50 | 73.17 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #44 / 50 | 75.1 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #45 / 50 | 81.87 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #66 / 73 | 73.42 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #71 / 73 | 62.05 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #61 / 73 | 80.89 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #29 / 73 | 66.86 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #45 / 73 | 65.17 | ↑ higher | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.