Model profile
GPT-6.1 Sol
Evidence summary
Safety. GPT-6.1 Sol has an estimated Safety rank of #1; its 90% source-sensitivity interval is #1–#7. Published Safety evidence spans 6 eval lineages and 5 of 7 components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 131); its weakest is CheatBench direct cheating propensity (multimodal_cheating_rate_pct, #8 of 12).
Freedom. GPT-6.1 Sol has an estimated Freedom rank of #184; its 90% source-sensitivity interval is #25–#557. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (eq_boundaries, #5 of 92); its weakest is SM-Bench (adversarial, #53 of 92).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-6-1-sol
- OpenRouter ↗openai/gpt-6.1-sol
- Official launch announcement ↗Exact model document · openai · first party
- Release source ↗curated outward evidence
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 | #82 / 358 | ↓0.4936 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #21 / 122 | ↑0.62 | Source ↗official | |
| CheatBench direct cheating propensitybiology_bioinformatics_cheating_rate_pct | #1 / 12 | ↓10 | Source ↗official | |
| CheatBench direct cheating propensityboard_games_cheating_rate_pct | #4 / 12 | ↓22 | Source ↗official | |
| CheatBench direct cheating propensitycreative_writing_cheating_rate_pct | #5 / 12 | ↓80 | Source ↗official | |
| CheatBench direct cheating propensityknowledge_work_cheating_rate_pct | #8 / 12 | ↓95 | Source ↗official | |
| CheatBench direct cheating propensitymathematical_research_cheating_rate_pct | #4 / 12 | ↓77.5 | Source ↗official | |
| CheatBench direct cheating propensitymenial_computation_cheating_rate_pct | #5 / 12 | ↓100 | Source ↗official | |
| CheatBench direct cheating propensitymultimodal_cheating_rate_pct | #8 / 12 | ↓97.5 | Source ↗official | |
| CheatBench direct cheating propensitysvg_competition_cheating_rate_pct | #1 / 12 | ↓0 | Source ↗official | |
| Olam Diplomacy — Broken Promise Ratebroken_promise_rate_pct | #1 / 19 | ↓8 | Source ↗official | |
| SM-Benchadversarial | #37 / 92 | ↑83.41 | Source ↗official | |
| SM-Benchambiguous_interpretation | #36 / 92 | ↑87.5 | Source ↗official | |
| SM-Benchanti_hallucination | #31 / 92 | ↑96.86 | Source ↗official | |
| SM-Bencheq_boundaries | #5 / 92 | ↑78.09 | Source ↗official | |
| SM-Benchoverfit | #11 / 92 | ↑93.17 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 131 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #22 / 131 | ↓4.25 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #18 / 131 | ↓4.38 | Source ↗official | |
| SpeciEvalspeciesism | #17 / 131 | ↓1.48 | 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.