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
Proximal agent harness
协议
FrontierSWE v2; Proximal agent harness; max reasoning effort; mean over five trials per task.
条件
Long interactive puzzle-game tasks; near 20 hours per task is benchmark context, not an inferred model effort setting.
Claude Opus 5.5 · FrontierSWE · v2 · Scores and configurations
Claude Opus 5.5 record for FrontierSWE · v2. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Claude Opus 5.5 · FrontierSWE scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Mean score62.3%Reported 62.3% · Unit %
Published Unconfirmed
System Card max effort (per-result benchmark harnesses)
Settings
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.
Unknowns
Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
Tools
Tool access not recorded
Reasoning budget
max
Framework
Proximal agent harness
Protocol
FrontierSWE v2; Proximal agent harness; max reasoning effort; mean over five trials per task.
Conditions
Long interactive puzzle-game tasks; near 20 hours per task is benchmark context, not an inferred model effort setting.