Home Model series Claude Fable Claude Fable 5.2 Claude Fable 5.2 · ProgramBench · 166 个保留的 golden tasks;架构与时限按协议区分 · Scores and configurations Claude Fable 5.2 · ProgramBench · 166 个保留的 golden tasks;架构与时限按协议区分 · Scores and configurations Claude Fable 5.2 record for ProgramBench · 166 个保留的 golden tasks;架构与时限按协议区分. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Fable 5.2 · ProgramBench scores and configurations Metric and score Configuration and evaluation conditions Sources Hidden test pass rate 85.6% Reported 85.6% · Unit % Published Unconfirmed
ProgramBench without remaining-context display Settings Claude Fable 5.2;single-agent mini-swe-agent harness;1M-token context;remaining context tokens are not shown;max effort。 Unknowns none recorded Tools Tool access not recorded Reasoning budget max Framework single-agent mini-SWE-agent harness Protocol ProgramBench 166-task golden subset; single-agent mini-swe-agent harness; no internet/decompilation; hidden-test pass rate. Conditions 1M-token context with no remaining-context indicator; max effort. Hidden test pass rate 91.6% Reported 91.6% · Unit % Published Unconfirmed
ProgramBench with remaining-context display Settings Claude Fable 5.2;single-agent mini-swe-agent harness;1M-token context;remaining context tokens are shown after each step;max effort。 Unknowns none recorded Tools Tool access not recorded Reasoning budget max Framework single-agent mini-SWE-agent harness Protocol ProgramBench 166-task golden subset; single-agent mini-swe-agent harness; no internet/decompilation; hidden-test pass rate. Conditions 1M-token context with remaining-context tokens shown after each step; max effort.
Benchmark versions and metrics Aliases ProgramBench、Multi-Agent ProgramBench
Hidden test pass rate · % · Higher is better Score · Unit not specified · Higher is better