Model profile
Qwen3.8 Max
Alibabadeveloper
2026-08-03release date
#93 / 312overall rank
6eval lineages
1discovery sources
Evidence summary
Qwen3.8 Max has an estimated overall rank of #93; its 90% source-sensitivity interval is #18–#241. Its behavior-only rank is #85; company governance moves the combined estimate to #93. Published evidence spans 6 evals and 6 of 7 behavior components. Its strongest relative result is Manager Coercion Bench (fabrication_rate, #1 of 15); its weakest is TAC (base_welfare_rate, #71 of 76).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-8-max
- Hugging Face ↗Qwen/Qwen3.8-2.4T-A95B
- OpenRouter ↗qwen/qwen3.8-max
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗curated outward evidence
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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #39 / 330 | ↓0.3918 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #9 / 33 | ↓7.6 | Source ↗official | |
| Manager Coercion Benchfabrication_rate | #1 / 15 | ↓0 | Source ↗official | |
| SM-Benchadversarial | #23 / 79 | ↑84.39 | Source ↗official | |
| SM-Benchambiguous_interpretation | #58 / 79 | ↑80.65 | Source ↗official | |
| SM-Benchanti_hallucination | #72 / 79 | ↑76.96 | Source ↗official | |
| SM-Bencheq_boundaries | #6 / 79 | ↑75.84 | Source ↗official | |
| SM-Benchoverfit | #60 / 79 | ↑52.19 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #37 / 113 | ↑6.88 | Source ↗official | |
| SpeciEvalland_animal_4ns | #24 / 113 | ↓4.28 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #17 / 113 | ↓4.47 | Source ↗official | |
| SpeciEvalspeciesism | #61 / 113 | ↓2.08 | Source ↗official | |
| TACbase_welfare_rate | #71 / 76 | ↑16.67 | Source ↗official | |
| WildClawBench Safety & Alignment (OpenClaw harness)safety_alignment_score_pct | #7 / 24 | ↑42 | Source ↗official |