Qwen Max · 发布历史
Alibaba Group Qwen Max 系列已收录 2 次发布和 48 个测试版本。
Qwen Max 托管 API 型号系列;API model ID、服务配置与开放权重型号分别记录。
全部版本
- Qwen4-Max17 项测试
- Qwen3.8-Max31 项测试
已收录测试 · 48
- DeepSWE · 1.1 · 指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- CodeArena · 版本未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- Terminal-Bench · 4.0 · 指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- ProgramBench · 版本/指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- AA-Briefcase · v1.1Qwen4-Max
- Agents’ Last Exam · 1.1 · 题集/指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- JobBench · 更新题集 · 版本未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- APEX-Agents · 1.1 · 指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- HLAB-Vals · 1.1 · 指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- AutomationBench-AA · AA · 版本/指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- AgentArena · Net Improvement;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- BioMysteryBench · 版本/题集/指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- HealthBench Professional · 校正口径/单位未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- Humanity’s Last Exam · 题集/工具/单位未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- ChartoGraphy · 题集/工具/单位未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- Video-Index · 版本/指标未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- Work360 · 原始得分 · 版本未注明;Qwen4-Max官方主图/正文;未注明的评测细节保持未知Qwen4-Max
- Terminal-Bench · 2.1; evaluated with Claude Code at avg@10, 5-hour timeout, max_tokens=131,072; metric scale unspecifiedQwen3.8-Max
- SWE-bench Pro · 版本/单位未注明 (qg-completion-qwen38-max-api-swe-bench-pro)Qwen3.8-Max
- DeepSWE 1.1 · 版本/单位未注明 (qg-completion-qwen38-max-api-deepswe-1-1)Qwen3.8-Max
- NL2Repo-Bench · Task version and metric scale not stated in the comparison tableQwen3.8-Max
- FrontierSWE · MEAN@5 leaderboard score as of 2026-08-03; task release/version not statedQwen3.8-Max
- MLS-Bench-Lite · Task version and metric scale not stated in the comparison tableQwen3.8-Max
- PaperBench · Subset and metric scale not stated in the comparison tableQwen3.8-Max
- AndroidBench · 95-task public subset; avg@3; score scale not statedQwen3.8-Max
- QwenSWEBench · In-house coding benchmark; avg@3; 8-hour timeout; task release not statedQwen3.8-Max
- QwenQoderBench · In-house Qoder UX benchmark; avg@5; 6-hour timeout; task release not statedQwen3.8-Max
- QwenReactBench · In-house bilingual seven-category React benchmark; auto-render and multimodal judgeQwen3.8-Max
- QwenSVGBench · In-house bilingual SVG benchmark; auto-render and multimodal judge; task release not statedQwen3.8-Max
- CoWorkBench · In-house long-horizon cowork benchmark; task set and metric scale not statedQwen3.8-Max
- WorkSpaceBench · Task version and metric scale not stated in the comparison tableQwen3.8-Max
- JobBench · Task version and metric scale not stated in the comparison tableQwen3.8-Max
- SkillsBench · Public v1.1; 87 tasks; average over three runs; score scale not statedQwen3.8-Max
- Agents' Last Exam · 版本/单位未注明 (qg-completion-qwen38-max-api-agents-last-exam)Qwen3.8-Max
- Automation-Bench · 600-task public subset; Pass@1; task release and unit not statedQwen3.8-Max
- Toolathlon Verified · Verified subset and task release not stated; Pass@1Qwen3.8-Max
- WideSearch · Task version not stated; average item-F1 over four runsQwen3.8-Max
- HLE · HLE with tools; question-set scope, metric and unit not stated in the cited tableQwen3.8-Max
- GPQA Diamond · 版本/单位未注明 (qg-completion-qwen38-max-api-gpqa-diamond)Qwen3.8-Max
- HLE · HLE label only; question-set scope, metric and unit not stated in the cited tableQwen3.8-Max
- IFBench · 版本/单位未注明 (qg-completion-qwen38-max-api-ifbench)Qwen3.8-Max
- $OneMillion-Bench · Expert-score metric; task version and scale not statedQwen3.8-Max
- HealthBench · Task version, score variant, and metric scale not stated in the comparison tableQwen3.8-Max
- PLawBench · Task version and metric scale not statedQwen3.8-Max
- PRBench-Legal · Task version and metric scale not statedQwen3.8-Max
- PRBench-Finance · Task version and metric scale not statedQwen3.8-Max
- OpenAI MRCR · v2, 256K context, 8 needlesQwen3.8-Max
- LongBench v2 · Task version and metric scale not stated in the comparison tableQwen3.8-Max