* SWE-Bench Series: Internal agent scaffold (bash + file-edit tools); temp=1.0, top_p=0.95, 200K context window. We correct some problematic tasks in the public set of SWE-bench Pro and evaluate all baselines on the refined benchmark. 2026-11-17 核读:原表/图未标单位,撤回旧百分比标记;数值与原证据不变。 来源未明确逐行指标名称时改记为 reported-score;显式标签单独保留。
* SWE-Bench Series: Internal agent scaffold (bash + file-edit tools); temp=1.0, top_p=0.95, 200K context window. We correct some problematic tasks in the public set of SWE-bench Pro and evaluate all baselines on the refined benchmark. 2026-11-17 核读:原表/图未标单位,撤回旧百分比标记;数值与原证据不变。 来源未明确逐行指标名称时改记为 reported-score;显式标签单独保留。
Qwen · SWE-bench Pro · Version / Unit not specified (qg-completion-qwen36-swe-bench-pro) · Release history
View scores, configurations, and disclosures for SWE-bench Pro · Version / Unit not specified (qg-completion-qwen36-swe-bench-pro) across 2 Qwen releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
* SWE-Bench Series: Internal agent scaffold (bash + file-edit tools); temp=1.0, top_p=0.95, 200K context window. We correct some problematic tasks in the public set of SWE-bench Pro and evaluate all baselines on the refined benchmark. 2026-11-17 核读:原表/图未标单位,撤回旧百分比标记;数值与原证据不变。 来源未明确逐行指标名称时改记为 reported-score;显式标签单独保留。
* SWE-Bench Series: Internal agent scaffold (bash + file-edit tools); temp=1.0, top_p=0.95, 200K context window. We correct some problematic tasks in the public set of SWE-bench Pro and evaluate all baselines on the refined benchmark. 2026-11-17 核读:原表/图未标单位,撤回旧百分比标记;数值与原证据不变。 来源未明确逐行指标名称时改记为 reported-score;显式标签单独保留。