Qwen 3.8-Max

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: $OneMillion-Bench (expert score) · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Agents' Last Exam (ALE-CLI) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Pass

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Agents' Last Exam (Pass / Score) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Score

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Agents' Last Exam (Pass / Score) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: AndroidBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Automation-Bench (Pass@1) · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal professional work tasks across science,finance,law,medical,productivity.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: CoWorkBench · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: CyberGym · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: DeepSWE (v1.1) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Best of Claude Code and mini-SWE-agent; Qwen best Claude Code; temp1,top_p.95,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: DeepSWE 1.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitBench · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. 2h Single-run869tasks; API time normalized by model TPS plus overhead; reported number solved; domain whitelist.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitGym (2h / 6h) · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details. 6h Single-run869tasks; API time normalized by model TPS plus overhead; reported number solved; domain whitelist.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ExploitGym (2h / 6h) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: FrontierSWE · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

Externally evaluated result, attributed in the source footnote.

Comparison limit: The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison.

zai-org/GLM-5.3 · Performance table: GDPval-AA v2 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: GPQA Diamond · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HealthBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HLE · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: HLE w/ tools · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: HLE w/ Tools · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: IFBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: JobBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: LongBench v2 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: MLS-Bench-Lite · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: MRCR v2 256K (8-needle) · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: NL2Repo · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: NL2Repo-Bench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. BasicAgent Code-Dev; Opus4.6 judge,3runs,12h each.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PaperBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PLawBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PRBench-Finance · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: PRBench-Legal · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: ProgramBench (Almost Solved) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal Qoder tasks,ClaudeCode,avg@5,6h,32768 output,temp1,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenQoderBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal bilingual EN/CN React benchmark,7categories,ClaudeCode,render+multimodaljudge,BT/Elo.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenReactBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal bilingual EN/CN SVG benchmark,render+multimodaljudge,BT/Elo.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenSVGBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Internal software engineering,ClaudeCode,avg@3,8h,32768 output,temp1,256K.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: QwenSWEBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. v1.1 public87tasks,3runs; Anthropic ClaudeCode,OpenAI Codex,Qwen OpenCode.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: SkillsBench · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Refined task set with problematic tasks corrected; all baselines rerun, Claude Code,temp1,top_p.95,256K context.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: SWE-bench Pro · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Toolathlon Verified · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Toolathlon Verified (Pass@1) · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Item-F1 over4runs; Qwen-Agent for Qwen,ClaudeCode for comparators.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: WideSearch · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: WorkSpaceBench · reviewed 2026-09-12