Qwen3.8-Max · SkillsBench(Public v1.1; 87 tasks; average over three runs; score scale not stated) 70.2 · 附件证据(ev-qwen-3-8-max-api-16)
Qwen3.8-Max 的 SkillsBench · Public v1.1; 87 tasks; average over three runs; score scale not stated 官方出处。QwenCloud API: qwen3.8-max · 70.2。见《Qwen3.8-2.4T-A95B official model card with explicit Qwen3.8-Max comparison column》Benchmark Results table / General Agent / SkillsBench / Qwen3.8-Max column。证据 ev-qwen-3-8-max-api-16。
原文与定位
Qwen3.8-Max · SkillsBench(Public v1.1; 87 tasks; average over three runs; score scale not stated),QwenCloud API: qwen3.8-max配置,Average score 70.2(具体成绩公布时间未确认)。见《Qwen3.8-2.4T-A95B official model card with explicit Qwen3.8-Max comparison column》Benchmark Results table / General Agent / SkillsBench / Qwen3.8-Max column。 查看成绩条件
| | Opus 4.8 | Fable 5 | GPT 5.6 Sol (max) | Qwen3.7-Max | Qwen3.8-Max | General Agent | SkillsBench | 65.1 | 70.9 | 73.5 | 61.2 | 70.2 | 15. SkillsBench: Evaluated on the public SkillsBench v1.1 benchmark across 87 tasks, reporting the average score over three runs per task. Opus 4.8 and Fable 5 are evaluated on Claude Code; GPT-5.6 Sol is evaluated on Codex; the Qwen-series are evaluated on OpenCode. All results are from our own testing.
- 官方材料
- Qwen3.8-2.4T-A95B official model card with explicit Qwen3.8-Max comparison column
- 定位
- 附件 · Benchmark Results table / General Agent / SkillsBench / Qwen3.8-Max column
- 材料版本
- 2026-11-17当前材料快照;完整读取Qwen3.8-2.4T-A95B官方模型卡正文和比较表的全部32行、相关脚注;仅录明确Qwen3.8-Max列。除脚注明示BT/Elo的两项外,表中分数未标单位。
- 版本公布
- 未确认
- 披露时间
- 未确认 · 后补披露
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
Qwen3.8-Max · SkillsBench(Public v1.1; 87 tasks; average over three runs; score scale not stated),QwenCloud API: qwen3.8-max配置,Average score 70.2(具体成绩公布时间未确认)。官方出处 Qwen3.8-2.4T-A95B official model card with explicit Qwen3.8-Max comparison column(附件,2026-11-17当前材料快照;完整读取Qwen3.8-2.4T-A95B官方模型卡正文和比较表的全部32行、相关脚注;仅录明确Qwen3.8-Max列。除脚注明示BT/Elo的两项外,表中分数未标单位。)Benchmark Results table / General Agent / SkillsBench / Qwen3.8-Max column,https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B。Benchlog https://benchlog.lekshome.cc/evidence/qwen-3-8-max-api/ev-qwen-3-8-max-api-16/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Average score70.2原文 70.2 · 单位 未标注 公布 未确认 | QwenCloud API: qwen3.8-max
| 直接支持该成绩 在排名中查看此成绩 |