Model profile
Qwen3 Next 80B A3B
Evidence summary
Qwen3 Next 80B A3B has an estimated overall rank of #108; its 90% source-sensitivity interval is #70–#202. Its behavior-only rank is #99; company governance moves the combined estimate to #108. Published evidence spans 10 evals and 6 of 7 behavior components. Its strongest relative result is HELM Safety (anthropic_red_team, #2 of 80); its weakest is Alignment Leaderboard (honesty, #21 of 24).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-next-80b-a3b-reasoning
- Hugging Face ↗Qwen/Qwen3-Next-80B-A3B-Thinking
- OpenRouter ↗qwen/qwen3-next-80b-a3b-thinking
- 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 |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #174 / 311 | 0.8221 | ↓ lower | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #8 / 80 | 0.867 | ↑ higher | Source ↗official | |
| Alignment Leaderboardcorrigibility | #21 / 24 | 4.039 | ↑ higher | Source ↗official | |
| Alignment Leaderboardhonesty | #21 / 24 | 3.207 | ↑ higher | Source ↗official | |
| Alignment Leaderboardnon_manipulation | #16 / 24 | 3.197 | ↑ higher | Source ↗official | |
| Alignment Leaderboardrobustness | #13 / 24 | 3.427 | ↑ higher | Source ↗official | |
| Alignment Leaderboardsafety | #14 / 24 | 3.808 | ↑ higher | Source ↗official | |
| Alignment Leaderboardscheming | #16 / 24 | 3.56 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #54 / 105 | 38.78 | ↓ lower | Source ↗official | |
| HELM Safetyanthropic_red_team | #2 / 80 | 0.999 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #51 / 80 | 0.917 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #29 / 80 | 0.846 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #28 / 80 | 0.995 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #8 / 80 | 0.983 | ↑ higher | Source ↗official | |
| RefusalBenchyouden_j | #9 / 19 | 0.4545 | ↑ 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.