Claude Opus · SWE-bench Multimodal · Multimodal · 历代记录

按发布时间查看 Claude Opus 的 4 次发布在 SWE-bench Multimodal · Multimodal 的成绩、配置与披露。

仅为直接前代间的唯一、有效精确值计算差值,要求单位、指标与明确记录的配置和条件一致。

Claude Opus 4.7

· 本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)

Claude Opus 4.7 · SWE-bench Multimodal 成绩与配置
指标与成绩配置与评测条件出处
Pass rate34.5%原文 34.5% · 单位 %
公布 未确认
发布表报告值
设置
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
未知项
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
SWE-bench Multimodal; visual context such as screenshots and design mockups.
条件
Published in the capability summary; evaluated on an internal harness (Appendix 8.3), so retain the harness qualifier and do not present as an externally reproduced run.
在排名中查看此成绩

Claude Opus 4.8

· 本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)

与直接前代的记录缺少满足差值计算的同条件依据。

Claude Opus 4.8 · SWE-bench Multimodal 成绩与配置
指标与成绩配置与评测条件出处
Pass rate38.4%原文 38.4% · 单位 %
公布 未确认
System Card 默认配置
设置
除章节另有说明外,adaptive thinking at max effort,默认 temperature/top_p,平均 5 trials;评测上下文依任务而定且不超过 1M tokens。
未知项
未另记
工具
工具条件未记录
推理预算
max
框架
未记录
协议
SWE-bench Multimodal; average over 5 trials.
条件
System card identifies an internal harness and points to §9.3 of the Opus 4.7 System Card for evaluation details.
在排名中查看此成绩

Claude Opus 5

· 本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)

与直接前代的记录缺少满足差值计算的同条件依据。

Claude Opus 5 · SWE-bench Multimodal 成绩与配置
指标与成绩配置与评测条件出处
Pass rate59.4%原文 59.4% · 单位 %
公布 未确认
Adaptive thinking · max effort (card-wide default)
设置
System Card §8.1 default: adaptive thinking at max effort, default sampling settings (temperature/top_p), averaged over five trials unless otherwise noted; context varies by evaluation and does not exceed 1M tokens.
未知项
Per-benchmark exceptions and harness details are recorded on the relevant configurations/results.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
SWE-bench Multimodal; screenshot/mockup context; see §9.3 internal harness.
条件
Five-trial average; card-wide default adaptive max effort; harness details are in Appendix §9.3.
在排名中查看此成绩

Claude Opus 5.5

· 本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)

与直接前代的记录缺少满足差值计算的同条件依据。

Claude Opus 5.5 · SWE-bench Multimodal 成绩与配置
指标与成绩配置与评测条件出处
Pass rate61.4%原文 61.4% · 单位 %
公布 未确认
System Card max effort (per-result benchmark harnesses)
设置
System Card §8.1 default: adaptive thinking/max effort and default sampling settings unless a section says otherwise. Benchmark tools, evaluator, safeguards, fallback, and repetitions remain per-result conditions; this config represents the stated model effort, not harness equivalence.
未知项
Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Visual issue context including screenshots and design mockups; five trials averaged.
条件
Exact task count, tools and run date are not stated. Source-wide conditions: Each score is averaged over five trials; Multilingual has 300 problems across nine languages.
在排名中查看此成绩