Model profile
Intellect 3
Evidence summary
Safety. Intellect 3 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 3 eval lineages and 1 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #243 of 345); its weakest is BullshitBench v2 (clear_pushback_rate, #107 of 117).
Freedom. Intellect 3 has an estimated Freedom rank of #358; its 90% source-sensitivity interval is #182–#514. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SpeechMap model completion (complete_pct, #60 of 181); its weakest is SpeechMap model completion (complete_pct, #60 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗intellect-3
- Hugging Face ↗PrimeIntellect/INTELLECT-3-FP8
- OpenRouter ↗prime-intellect/intellect-3
- Official model page ↗Configuration-level model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #243 / 345 | ↓0.8759 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #83 / 111 | ↑1419.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #107 / 117 | ↑0.06 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| SpeechMap model completioncomplete_pct | #60 / 181 | ↑69.2 | Source ↗official |