Home Model series Claude Opus Claude Opus 4.6 Claude Opus 4.6 · GraphWalks · 256K-context subset of the 256K-1M evaluation; item count unspecified; parents · Scores and configurations Claude Opus 4.6 · GraphWalks · 256K-context subset of the 256K-1M evaluation; item count unspecified; parents · Scores and configurations Claude Opus 4.6 record for GraphWalks · 256K-context subset of the 256K-1M evaluation; item count unspecified; parents. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Opus 4.6 · GraphWalks scores and configurations Metric and score Configuration and evaluation conditions Sources Parents F1 95.1% Reported 95.1 (64k) · Unit % Published Unconfirmed
GraphWalks Parents · API-compatible subset · 64K Settings GraphWalks 1M variant 中可在公开 API 1M 上限内复现的 256K-context subset;64K extended thinking;effort 未说明。 Unknowns 64K 是 extended-thinking 设置,不据此推断 effort。 Tools Tool access not recorded Reasoning budget Thinking budget 64K Framework not recorded Protocol GraphWalks Parents 256K-context API-compatible subset of 1M variant;F1 score。 Conditions 5-run average;subset filtered within 1M public API limit; 64K extended thinking; effort unknown。 View this score in rankings Parents F1 95.4% Reported 95.4 (max) · Unit % Published Unconfirmed
GraphWalks Parents · API-compatible subset · Max Settings GraphWalks 1M variant 中可在公开 API 1M 上限内复现的 256K-context subset;Max effort。 Unknowns none recorded Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol GraphWalks Parents 256K-context API-compatible subset of 1M variant;F1 score。 Conditions 5-run average;subset filtered within 1M public API limit; max effort。 View this score in rankings
Benchmark versions and metrics Aliases GraphWalks 256K-context subset parents
Parents F1 · % · Higher is better