Model profile
OLMo 3 7B Instruct
Evidence summary
Safety. OLMo 3 7B Instruct has an estimated Safety rank of #138; its 90% source-sensitivity interval is #46–#304. Its behavior-only rank is #139; company governance moves the combined estimate to #138. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is IndoBias-Pairs — parity-aware culturally grounded bias (parity_score, #2 of 26); its weakest is AA-Omniscience (hallucination_rate, #285 of 345).
Freedom. OLMo 3 7B Instruct has an estimated Freedom rank of #595; its 90% source-sensitivity interval is #340–#633. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_direct_score, #79 of 156); its weakest is UGI Leaderboard — base-model willingness (willingness_adherence_score, #144 of 156).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗olmo-3-7b-instruct
- Hugging Face ↗allenai/Olmo-3-7B-Instruct
- OpenRouter ↗allenai/olmo-3-7b-instruct
- Official model page ↗Exact 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 | #285 / 345 | ↓0.9122 | Source ↗official | |
| AuAu Authoritarian Response Auditbehavioral_vignette_arr_percent | #7 / 17 | ↓24.9 | Source ↗official | |
| AuAu Authoritarian Response Auditrealistic_prompt_arr_percent | #6 / 17 | ↓1.4 | Source ↗official | |
| IndoBias-Pairs — parity-aware culturally grounded biasparity_score | #2 / 26 | ↑91.81 | 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 | #142 / 181 | ↑40.7 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #144 / 156 | ↑0.5 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #79 / 156 | ↑3 | 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.