Model profile
Olmo 2 1124 7B Instruct
Ai2developer
2024-11-26release date
#258 / 267overall rank
6eval lineages
Evidence summary
Olmo 2 1124 7B Instruct has an estimated overall rank of #258; its 90% source-sensitivity interval is #196–#262. Its behavior-only rank is #262; company governance moves the combined estimate to #258. Published evidence spans 6 evals and 5 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #69 of 260); its weakest is HELM Safety (bbq, #79 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗allenai/OLMo-2-1124-7B-Instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #219 / 260 | 10.59 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #103 / 260 | 89.67 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #69 / 260 | 86.67 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #92 / 258 | 97.82 | ↑ higher | Source ↗official | |
| HELM Safetyanthropic_red_team | #78 / 80 | 0.88 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #79 / 80 | 0.525 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #63 / 80 | 0.578 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #77 / 80 | 0.775 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #71 / 80 | 0.888 | ↑ higher | Source ↗official |